diff --git a/.dockerignore b/.dockerignore
new file mode 100644
index 0000000000000000000000000000000000000000..b76be564cbde84ae29f4b3f74cf76c24f317cc3d
--- /dev/null
+++ b/.dockerignore
@@ -0,0 +1,3 @@
+/.venv
+dist
+__pycache__/
diff --git a/.env-docker b/.env-docker
new file mode 100644
index 0000000000000000000000000000000000000000..faf2924e358ed7bdcd84046a2cf3d9393d21d281
--- /dev/null
+++ b/.env-docker
@@ -0,0 +1,8 @@
+weight_root=/weights
+weight_uvr5_root=/assets/uvr5_weights
+index_root=/indices
+rmvpe_root=/assets/rmvpe
+hubert_path=/assets/hubert_base.pt
+save_uvr_path=/assets/uvr5_weights
+TEMP=/app/TEMP
+pretrained=/assets/pretrained
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..ebdbe070cc4131df22afb24abc638ef6a5428c3e
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,8 @@
+/.venv
+/assets
+dist
+__pycache__/
+*.py[cod]
+*$py.class
+
+.DS_Store
diff --git a/Dockerfile b/Dockerfile
index aa9e1acf98cf0784e0bed709f8f8db5e6cfe08b7..b5a0a28b9b1bb79eacbbc8840dcadec12525672a 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,19 +1,47 @@
-FROM python:3.10-slim
+FROM alpine:3.19.1 as assets
 
-WORKDIR /app
+RUN apk add \
+      --update \
+      --no-cache \
+        bash \
+        git \
+        git-lfs\
+        dos2unix
+
+COPY --chmod=755 ./assets-download.sh /assets-download.sh
+
+#convert malformed line endings if cloned from Windows
+RUN dos2unix /assets-download.sh
+
+RUN /assets-download.sh 88e42f0cb3662ddc0dd263a4814206ce96d53214 assets
+
+FROM python:3.10.14-bullseye as app
 
-# System deps
-RUN apt-get update && apt-get install -y ffmpeg git && rm -rf /var/lib/apt/lists/*
+SHELL [ "/bin/bash", "-c" ]
+
+RUN apt update && \
+    apt install -y \
+      libsndfile1 \
+      libsndfile1-dev && \
+    apt clean && \
+    rm -rf /var/lib/apt/lists/*
+
+COPY --from=assets /assets /assets
+
+WORKDIR /app
 
-# Python deps
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+COPY ./pyproject.toml .
 
-# Copy app + models
-COPY app/ ./app/
-COPY rvc/ ./rvc/
-COPY models/ ./models/
+RUN pip install \
+      --no-cache-dir \
+      "poetry==1.7.1" && \
+    poetry config virtualenvs.create false && \
+    poetry install \
+      --no-interaction \
+      --no-root && \
+    poetry cache clear --all .
 
-EXPOSE 7860
+COPY ./rvc ./rvc
+COPY ./.env-docker ./.env
 
-CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]
+CMD [ "poetry", "run", "poe", "rvc-api" ]
diff --git a/api-request.sh b/api-request.sh
new file mode 100644
index 0000000000000000000000000000000000000000..41979ebfe756db24a6df41026bcc8c09092ae811
--- /dev/null
+++ b/api-request.sh
@@ -0,0 +1,59 @@
+#!/usr/bin/env bash
+#
+# Runs request to RVC API on localhost.
+
+set -e
+
+host="http://127.0.0.1:8000"
+
+url="${host}/inference"
+
+url+="?res_type=json"
+
+model_path=""
+index_path=""
+input_audio=""
+output_audio_suffix=""
+
+while [ $# -gt 0 ]; do
+  if [ "$1" == "--model_path" ]; then
+    model_path="$2"
+  elif [ "$1" == "--index_file" ]; then
+    index_path="$2"
+  elif [ "$1" == "--input_audio" ]; then
+    input_audio="$2"
+  else
+    arg_name="${1#--}"
+    arg_value="$2"
+
+    url+="&${arg_name}=${arg_value}"
+    output_audio_suffix+="-${arg_name}_${arg_value}"
+  fi
+
+  shift
+  shift
+done
+
+model_path_base="$(basename "${model_path}")"
+model_path_base_without_ext="${model_path_base%.*}"
+index_path_base="$(basename "${index_path}")"
+input_audio_base="$(basename "${input_audio}")"
+input_audio_dirname="$(dirname "${input_audio}")"
+output_audio_base_without_ext="${input_audio_base%.*}"
+output_audio="${input_audio_dirname}/${output_audio_base_without_ext}-${model_path_base_without_ext}${output_audio_suffix}.wav"
+
+cp "${model_path}" "./assets/weights/${model_path_base}"
+cp "${input_audio}" "./assets/audios/${input_audio_base}"
+
+if [ -f "${index_path}" ]; then
+  url+="&index_file=${index_path_base}"
+  cp "${index_path}" "./assets/indices/${index_path_base}"
+fi
+
+curl -X "POST" "${url}" \
+  -H "accept: application/json" \
+  -H "Content-Type: multipart/form-data" \
+  -F "modelpath=${model_path_base}" \
+  -F "input_audio=/audios/${input_audio_base}" \
+| jq -r '.audio' \
+| base64 -d > "${output_audio}"
diff --git a/assets-download.sh b/assets-download.sh
new file mode 100644
index 0000000000000000000000000000000000000000..83d7f53a04e9ccf42d7bf88982377e865ca3ff49
--- /dev/null
+++ b/assets-download.sh
@@ -0,0 +1,52 @@
+#!/usr/bin/env bash
+#
+# Downloads required large files for RVC.
+
+function download() {
+  local path="$1"
+  echo "Downloading ${path}"
+  git lfs pull --include="${path}"
+}
+
+set -e
+
+REPO_FOLDER="VoiceConversionWebUI"
+
+assets_commit_hash="$1"
+assets_dir="$2"
+
+export GIT_CLONE_PROTECTION_ACTIVE=false
+export GIT_LFS_SKIP_SMUDGE=1
+
+git clone https://huggingface.co/lj1995/VoiceConversionWebUI "${REPO_FOLDER}"
+
+pushd "${REPO_FOLDER}"
+
+git config advice.detachedHead false
+
+git checkout "${assets_commit_hash}"
+
+unset GIT_LFS_SKIP_SMUDGE
+unset GIT_CLONE_PROTECTION_ACTIVE
+
+download "hubert_base.pt"
+download "pretrained"
+download "uvr5_weights"
+download "rmvpe.pt"
+download "rmvpe.onnx"
+
+rm -rf .git
+
+popd
+
+mkdir -p "${assets_dir}"
+
+mv "${REPO_FOLDER}/hubert_base.pt" "${assets_dir}/hubert_base.pt"
+
+mkdir -p "${assets_dir}/rmvpe"
+
+mv "${REPO_FOLDER}/rmvpe.pt" "${assets_dir}/rmvpe/rmvpe.pt"
+mv "${REPO_FOLDER}/rmvpe.onnx" "${assets_dir}/rmvpe/rmvpe.onnx"
+
+mv "${REPO_FOLDER}/pretrained" "${assets_dir}/pretrained"
+mv "${REPO_FOLDER}/uvr5_weights" "${assets_dir}/uvr5_weights"
diff --git a/docker-run.sh b/docker-run.sh
new file mode 100644
index 0000000000000000000000000000000000000000..a9bf5a7bd493b5a719cf75cb2599f8816e1c39b6
--- /dev/null
+++ b/docker-run.sh
@@ -0,0 +1,16 @@
+#!/usr/bin/env bash
+#
+# Runs RVC API in Docker.
+
+set -e
+
+tag="rvc"
+
+docker build -t "${tag}" .
+
+docker run -it \
+  -p 8000:8000 \
+  -v "${PWD}/assets/weights:/weights:ro" \
+  -v "${PWD}/assets/indices:/indices:ro" \
+  -v "${PWD}/assets/audios:/audios:ro" \
+  "${tag}"
diff --git a/docs/es/README.es.md b/docs/es/README.es.md
new file mode 100644
index 0000000000000000000000000000000000000000..eb322c36f96de90d7931183b1808e806b2cc1e62
--- /dev/null
+++ b/docs/es/README.es.md
@@ -0,0 +1,171 @@
+<div align="center">
+
+<h1>Retrieval-based-Voice-Conversion</h1>
+Un framework de conversión de voz basado en VITS y fácil de usar.<br><br>
+
+[![madewithlove](https://img.shields.io/badge/hecho_con-%E2%9D%A4-red?style=for-the-badge&labelColor=orange
+)](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion)
+
+<img src="https://counter.seku.su/cmoe?name=rvc&theme=r34" /><br>
+
+[![Licence](https://img.shields.io/github/license/RVC-Project/Retrieval-based-Voice-Conversion?style=for-the-badge)](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion/blob/develop/LICENSE)
+
+[![Discord](https://img.shields.io/badge/Desarrolladores%20de%20RVC-Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/HcsmBBGyVk)
+
+</div>
+
+------
+
+
+> [!NOTE]
+> Actualmente en desarrollo... Proporcionado como biblioteca y API en rvc
+
+## Instalación y uso
+
+### Instalación estándar
+
+Primero, cree un directorio en su proyecto. La carpeta `assets` contendrá los modelos necesarios para la inferencia y el entrenamiento, y la carpeta `results` contendrá los resultados del entrenamiento.
+
+```sh
+rvc init
+```
+Esto creará la carpeta `assets` y `.env` en su directorio de trabajo.
+
+> [!WARNING]
+> El directorio debe de estar vacío o sin una carpeta de assets.
+
+### Instalación personalizada
+
+Si ya has descargado modelos o deseas cambiar estas configuraciones, edita el archivo `.env`.
+Si aún no tienes el archivo `.env`,
+
+```sh
+rvc env create
+```
+puedes crearlo.
+
+Además, para descargar un modelo, puedes utilizar
+
+```sh
+rvc dlmodel
+```
+o
+```
+rvc dlmodel {download_dir}
+```
+
+Finalmente, especifique la ubicación del modelo en el archivo env y estará listo.
+
+
+
+### Uso de la librería
+
+#### Inferir un audio
+```python
+from pathlib import Path
+
+from dotenv import load_dotenv
+from scipy.io import wavfile
+
+from rvc.modules.vc.modules import VC
+
+
+def main():
+      vc = VC()
+      vc.get_vc("{model.pth}")
+      tgt_sr, audio_opt, times, _ = vc.vc_inference(
+            1, Path("{InputAudio}")
+      )
+      wavfile.write("{OutputAudio}", tgt_sr, audio_opt)
+
+
+if __name__ == "__main__":
+      load_dotenv("{envPath}")
+      main()
+
+```
+
+### Uso en CLI
+
+#### Inferir un audio
+
+```sh
+rvc infer -m {model.pth} -i {input.wav} -o {output.wav}
+```
+
+| opción        | flag&nbsp; | tipo         | valor por defecto | descipción                                                                                                                                                                                                                                    |
+|---------------|------------|--------------|---------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| modelPath     | -m         | Path         | *requerido     | Ruta del modelo o nombre de archivo (se lee en el directorio establecido en env)                                                                                                                                                                                     |
+| inputPath     | -i         | Path         | *requerido     | Ruta o carpeta del audio de entrada                                                                                                                                                                                                                     |
+| outputPath    | -o         | Path         | *requerido     | Ruta o carpeta del audio de salida                                                                                                                                                                                                                    |
+| sid           | -s         | int          | 0             | ID del Orador/ Cantante                                                                                                                                                                                                                              |
+| f0_up_key     | -fu        | int          | 0             | Transponer (número entero, número de semitonos, subir una octava: 12, bajar una octava: -12)                                                                                                                                                      |
+| f0_method     | -fm        | str          | rmvpe         | Algoritmo de extracción de tono (pm, harvest, crepe, rmvpe)                                                                                                                                                                                          |
+| f0_file       | -ff        | Path \| None | None          | Archivo de curva F0 (opcional). Un tono por línea. Reemplaza el F0 predeterminado y la modulación de tono.                                                                                                                                                     |
+| index_file    | -if        | Path \| None | None          | Ruta al archivo index de características                                                                                                                                                                                                                 |
+| index_rate    | -if        | float        | 0.75          | Proporción de funciones de búsqueda (controla la fuerza del acento, demasiado alta tiene artifacting)                                                                                                                                                                      |
+| filter_radius | -fr        | int          | 3             | Si >=3: aplique el filtrado de mediana a los resultados del tono. El valor representa el radio del filtro y puede reducir la respiración                                                                                                               |
+| resample_sr   | -rsr       | int          | 0             | Vuelva a muestrear el audio de salida en el posprocesamiento hasta la frecuencia de muestreo final. Establecer en 0 para no remuestreo                                                                                                                                              |
+| rms_mix_rate  | -rmr       | float        | 0.25          | Ajuste la escala de la envolvente del volumen. Cuanto más cerca de 0, más imita el volumen de las voces originales. Puede ayudar a enmascarar el ruido y hacer que el volumen suene más natural cuando se establece en un nivel relativamente bajo. Más cerca de 1 habrá un volumen más alto y constante |
+| protect       | -p         | float        | 0.33          | Proteja las consonantes sordas y los sonidos respiratorios para evitar artefactos como el desgarro en la música electrónica. Establezca en 0.5 para desactivarlo. Disminuya el valor para aumentar la protección, pero puede reducir la precisión de la indexación                                 |
+
+### Uso de la API
+Primero, inicia el servidor.
+```sh
+rvc-api
+```
+o
+```sh
+poetry run poe rvc-api
+```
+
+#### Inferir audio
+
+##### Obtener como blob
+```sh
+curl -X 'POST' \
+      'http://127.0.0.1:8000/inference?res_type=blob' \
+      -H 'accept: application/json' \
+      -H 'Content-Type: multipart/form-data' \
+      -F 'modelpath={model.pth}' \
+      -F 'input={input audio path}'
+```
+
+##### Obtener como json (incluir tiempo)
+```sh
+curl -X 'POST' \
+      'http://127.0.0.1:8000/inference?res_type=json' \
+      -H 'accept: application/json' \
+      -H 'Content-Type: multipart/form-data' \
+      -F 'modelpath={model.pth}' \
+      -F 'input={input audio path}'
+```
+
+### Uso con Docker
+
+Compilar y ejecutar usando el script:
+
+```bash
+./docker-run.sh
+```
+
+**O** usar manuálmente:
+
+1. Compilar:
+
+   ```bash
+   docker build -t "rvc" .
+   ```
+
+2. Ejecutar:
+
+   ```bash
+   docker run -it \
+     -p 8000:8000 \
+     -v "${PWD}/assets/weights:/weights:ro" \
+     -v "${PWD}/assets/indices:/indices:ro" \
+     -v "${PWD}/assets/audios:/audios:ro" \
+     "rvc"
+   ```
+
+Recuerda que los pesos (weights), índices y audios de entrada se almacenan en `directorio-actual/assets`
diff --git a/docs/jp/README.ja.md b/docs/jp/README.ja.md
new file mode 100644
index 0000000000000000000000000000000000000000..390364024ba38edb10432d3ef9bfb1683e2ed04b
--- /dev/null
+++ b/docs/jp/README.ja.md
@@ -0,0 +1,119 @@
+<div align="center">
+
+<h1>Retrieval-based-Voice-Conversion</h1>
+An easy-to-use Voice Conversion framework based on VITS.<br><br>
+
+[![madewithlove](https://img.shields.io/badge/made_with-%E2%9D%A4-red?style=for-the-badge&labelColor=orange
+)](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion)
+
+<img src="https://counter.seku.su/cmoe?name=rvc&theme=r34" /><br>
+
+[![Licence](https://img.shields.io/github/license/RVC-Project/Retrieval-based-Voice-Conversion?style=for-the-badge)](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion/blob/develop/LICENSE)
+
+[![Discord](https://img.shields.io/badge/RVC%20Developers-Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/HcsmBBGyVk)
+
+</div>
+
+------
+
+
+> [!NOTE]
+> 現在開発中です...rvcのライブラリとAPIを提供する予定です。
+
+## Installation and usage
+
+### Standard Setup
+
+最初にプロジェクトにディレクトリを作成します。`assets`フォルダには推論や学習に必要なモデル、`result`フォルダには学習の結果が保存されます。
+
+```sh
+rvc init
+```
+
+これにより、作業ディレクトリに`assets`フォルダと`.env`が作成されます。
+> [!WARNING]
+> この時、ディレクトリは空もしくは`assets`フォルダおよび`.env`ファイルがない状態にしてください
+
+### Custom Setup
+
+既にモデルをダウンロードしている場合や、これらの構成を変更したい場合、`.env`ファイルを編集してください。
+まだ`.env`ファイルがない場合、
+
+```sh
+rvc env create
+```
+
+にて作成できます。
+
+また、モデルをダウンロードするときは
+
+```sh
+rvc dlmodel
+```
+もしくは
+```
+rvc dlmodel {download_dir}
+```
+
+にてダウンロードできます。
+
+最後に、envファイルにてモデルの場所などを指定してあげれば、終了です！
+
+
+### CLI Usage
+
+#### Inference Audio
+
+```sh
+rvc infer -m {model.pth} -i {input.wav} -o {output.wav}
+```
+
+| option        | flag&nbsp; | type         | default value | description                                                                                                                                                                                                                                    |
+|---------------|------------|--------------|---------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| modelPath     | -m         | Path         | *required     | Model path or filename (reads in the directory set in env)                                                                                                                                                                                     |
+| inputPath     | -i         | Path         | *required     | Input audio path or folder                                                                                                                                                                                                                     |
+| outputPath    | -o         | Path         | *required     | Output audio path or folder                                                                                                                                                                                                                    |
+| sid           | -s         | int          | 0             | Speaker/Singer ID                                                                                                                                                                                                                              |
+| f0_up_key     | -fu        | int          | 0             | Transpose (integer, number of semitones, raise by an octave: 12, lower by an octave: -12)                                                                                                                                                      |
+| f0_method     | -fm        | str          | rmvpe         | pitch extraction algorithm (pm, harvest, crepe, rmvpe                                                                                                                                                                                          |
+| f0_file       | -ff        | Path \| None | None          | F0 curve file (optional). One pitch per line. Replaces the default F0 and pitch modulation                                                                                                                                                     |
+| index_file    | -if        | Path \| None | None          | Path to the feature index file                                                                                                                                                                                                                 |
+| index_rate    | -if        | float        | 0.75          | Search feature ratio (controls accent strength, too high has artifacting)                                                                                                                                                                      |
+| filter_radius | -fr        | int          | 3             | If >=3: apply median filtering to the harvested pitch results. The value represents the filter radius and can reduce breathiness                                                                                                               |
+| resample_sr   | -rsr       | int          | 0             | Resample the output audio in post-processing to the final sample rate. Set to 0 for no resampling                                                                                                                                              |
+| rms_mix_rate  | -rmr       | float        | 0.25          | Adjust the volume envelope scaling. Closer to 0, the more it mimicks the volume of the original vocals. Can help mask noise and make volume sound more natural when set relatively low. Closer to 1 will be more of a consistently loud volume |
+| protect       | -p         | float        | 0.33          | Protect voiceless consonants and breath sounds to prevent artifacts such as tearing in electronic music. Set to 0.5 to disable. Decrease the value to increase protection, but it may reduce indexing accuracy                                 |
+
+
+### API Usage
+最初に、サーバーを立ち上げます。
+```sh
+rvc-api
+```
+または
+```sh
+poetry run poe rvc-api
+```
+にて実行されます。
+
+#### Inference Audio
+
+##### blobでレスポンスを受け取る
+```sh
+curl -X 'POST' \
+      'http://127.0.0.1:8000/inference?res_type=blob' \
+      -H 'accept: application/json' \
+      -H 'Content-Type: multipart/form-data' \
+      -F 'modelpath={model.pth}' \
+      -F 'input={input audio path}'
+```
+
+##### jsonでレスポンス！(include time)
+```sh
+curl -X 'POST' \
+      'http://127.0.0.1:8000/inference?res_type=json' \
+      -H 'accept: application/json' \
+      -H 'Content-Type: multipart/form-data' \
+      -F 'modelpath={model.pth}' \
+      -F 'input={input audio path}'
+```
diff --git a/poetry.lock b/poetry.lock
new file mode 100644
index 0000000000000000000000000000000000000000..d4cf4a7b16b153f9f275effd4cb74c22a124a663
--- /dev/null
+++ b/poetry.lock
@@ -0,0 +1,2437 @@
+# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand.
+
+[[package]]
+name = "annotated-types"
+version = "0.6.0"
+description = "Reusable constraint types to use with typing.Annotated"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "annotated_types-0.6.0-py3-none-any.whl", hash = "sha256:0641064de18ba7a25dee8f96403ebc39113d0cb953a01429249d5c7564666a43"},
+    {file = "annotated_types-0.6.0.tar.gz", hash = "sha256:563339e807e53ffd9c267e99fc6d9ea23eb8443c08f112651963e24e22f84a5d"},
+]
+
+[[package]]
+name = "antlr4-python3-runtime"
+version = "4.9.3"
+description = "ANTLR 4.9.3 runtime for Python 3.7"
+optional = false
+python-versions = "*"
+files = [
+    {file = "antlr4-python3-runtime-4.9.3.tar.gz", hash = "sha256:f224469b4168294902bb1efa80a8bf7855f24c99aef99cbefc1bcd3cce77881b"},
+]
+
+[[package]]
+name = "anyio"
+version = "4.2.0"
+description = "High level compatibility layer for multiple asynchronous event loop implementations"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "anyio-4.2.0-py3-none-any.whl", hash = "sha256:745843b39e829e108e518c489b31dc757de7d2131d53fac32bd8df268227bfee"},
+    {file = "anyio-4.2.0.tar.gz", hash = "sha256:e1875bb4b4e2de1669f4bc7869b6d3f54231cdced71605e6e64c9be77e3be50f"},
+]
+
+[package.dependencies]
+exceptiongroup = {version = ">=1.0.2", markers = "python_version < \"3.11\""}
+idna = ">=2.8"
+sniffio = ">=1.1"
+typing-extensions = {version = ">=4.1", markers = "python_version < \"3.11\""}
+
+[package.extras]
+doc = ["Sphinx (>=7)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx-rtd-theme"]
+test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.17)"]
+trio = ["trio (>=0.23)"]
+
+[[package]]
+name = "audioread"
+version = "3.0.1"
+description = "Multi-library, cross-platform audio decoding."
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "audioread-3.0.1-py3-none-any.whl", hash = "sha256:4cdce70b8adc0da0a3c9e0d85fb10b3ace30fbdf8d1670fd443929b61d117c33"},
+    {file = "audioread-3.0.1.tar.gz", hash = "sha256:ac5460a5498c48bdf2e8e767402583a4dcd13f4414d286f42ce4379e8b35066d"},
+]
+
+[package.extras]
+test = ["tox"]
+
+[[package]]
+name = "av"
+version = "11.0.0"
+description = "Pythonic bindings for FFmpeg's libraries."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "av-11.0.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:a01f13b37eb6d181e03bbbbda29093fe2d68f10755795188220acdc89560ec27"},
+    {file = "av-11.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b2236faee1b5d71dff3cdef81ef6eec22cc8b71dbfb45eb037e6437fe80f24e7"},
+    {file = "av-11.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:40543a08e5c84aecd2bc84da5d43548743201897f0ba21bf5ae3a4dcddefca2b"},
+    {file = "av-11.0.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2907376884d956376aaf3bc1905fa4e0dcb9ba4e0d183e519392a19d89317d1b"},
+    {file = "av-11.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e8d5581dcdc81cd601e3ce036809f14da82c46ff187bcefe981ec819390e0ab0"},
+    {file = "av-11.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:150490f2a62cfa470f3cb60f3a0060ff93afd807e2b7b3b0eeeb5a992eb8d67b"},
+    {file = "av-11.0.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d9bac0de62f09e2cb4e2132b5a46a89bc31c898189aa285b484c17351d991afe"},
+    {file = "av-11.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2122ff8bdace4ce50207920f37de472517921e2ca1f0503464f748fdb8e20506"},
+    {file = "av-11.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:527d840697fee6ad4cf47eba987eaf30cd76bd96b2d20eaa907e166b9b8065c8"},
+    {file = "av-11.0.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:abeaedddfca9101886eb6fc47318c5f5ece8480d330d73aacf6917d7421981a2"},
+    {file = "av-11.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:13790fbb889b955baf885fe3761e923e85537ef414173465ec293177cedb7b99"},
+    {file = "av-11.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:fc27e27f52480287f44226ad4ae3eb53346bf027959d0f00a9154530bd98b371"},
+    {file = "av-11.0.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:892583e2c6b8c2500e5d24310f499caefcdaa2e48c8f7169ad41041aaaf4da11"},
+    {file = "av-11.0.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:6943679d70a9f4de974049e7ae2cf0b20afe0d7ddab650526c02a6cf9adcd08f"},
+    {file = "av-11.0.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e6d73b038ccf1df5c16bc643eee5c694fb7732e09375e2f4903c1f4ce90dfb72"},
+    {file = "av-11.0.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c83422db3333e97b9680700df5185139352fc3a568b14179da3bdcbeb2f0e91b"},
+    {file = "av-11.0.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8413900f6a3639e0088c018a3a516a1656d4d16799e7aa759a16ddf3bd268e2b"},
+    {file = "av-11.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:908e49ee336223801d8f2f7dca5a1deb64e9d8256138b8e7a79013b682a6ebb5"},
+    {file = "av-11.0.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:82411ae4a562da07b76028d2f349fb0e6a86aa78ad2b18d2d7bf5b06b17fba14"},
+    {file = "av-11.0.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:621104bd63e38fa4eca554da3722b1aac329619de39152f27eec8999acc72342"},
+    {file = "av-11.0.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:442878990c094455a16c10127edcc54bc4e78d355e6a13ad2a27608b0ecda38f"},
+    {file = "av-11.0.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:658199c92987dc72511f5ee8ade62faef6234b7a04c8b5788de99e366be5e073"},
+    {file = "av-11.0.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ad4b381665c49267b46f87297573898b85e5c41384750fee2e70267fbc4ba318"},
+    {file = "av-11.0.0-cp38-cp38-win_amd64.whl", hash = "sha256:60de14f71293e36ca4e297cc8a8460f0cf74f38a201694f3c6fc7f40301582f2"},
+    {file = "av-11.0.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:a90f04af96374dab94028a7471597bdfcf03083338b9be2eb8ca4805a8ec7ab5"},
+    {file = "av-11.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:8821ab2d23e4cb5c8abea6b08d2b1bfceca6af2d88fab1d1dc1b3ec7b34933c7"},
+    {file = "av-11.0.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9a92342ed307eeaf9509a6b0f3bafd4337c4880c851b50acc18df48c625b63b6"},
+    {file = "av-11.0.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bbe3502975bc844f5d432c1f24d331bf6ef3e05532ebf06f7ed08b60719b8ea5"},
+    {file = "av-11.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c278b3a4fd111b4c9190abe6b1a5ca358d5f91e851d470b62577b957e0187b09"},
+    {file = "av-11.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:478aa1d54fbc3058ea65ff41086b6adbe1326b456a027d2f3b59dbe60b4ac2ca"},
+    {file = "av-11.0.0-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:e8df10bb2d56a981d02a8a0b41491912b76dad06305d174a2575ef55ad451100"},
+    {file = "av-11.0.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b30c51e597785a89241bd61865faff2dbd3327856a8285a1e120dbf60e18348b"},
+    {file = "av-11.0.0-pp310-pypy310_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a8b8bd92edb096699b306e7b090ad096925ca3bdae6f89656f023fa2a2da627d"},
+    {file = "av-11.0.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9383af733abfc44f6fc29307a6c922fbf671ee343dc97b78b74eac6a2346a46d"},
+    {file = "av-11.0.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:a9df4a60579198b560f641cdfe4c2139948a70193ddc096b275f2cf6d94e3e04"},
+    {file = "av-11.0.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:8ae5f7ae0a7093fb813686d4aa4c554531f80a28480427f5c155da51b747eff0"},
+    {file = "av-11.0.0-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:50fb7d606f8236891d773c701d5650b93af8dbf78eeaac36fc7e1f7f64a9d664"},
+    {file = "av-11.0.0-pp38-pypy38_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:543e0f9bf6ff02dedbe66d906fbc89c8907c80a8ea7413fc3fed68ce4a6e9b44"},
+    {file = "av-11.0.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:daa279c884457ab194ce78bdd89c0aa391af733da95fb3258d4c6eb8c258299a"},
+    {file = "av-11.0.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:1aacc21f4cf96447117a61edfb776afb73186750a5e08a21484ddfc3599aefb5"},
+    {file = "av-11.0.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2568b38eef777b916a5d02e42b8f67f92e12023531239ddd32e1ca4f3cdf8c5b"},
+    {file = "av-11.0.0-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:747c6d347e27c59cc2e78c9c505d23cd88eceff0cc9386be73693ae9009a577c"},
+    {file = "av-11.0.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4bbd8f4941b9d3450eff40003b9b9d904667aec7ab085fa31f0f9bca32d755e0"},
+    {file = "av-11.0.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:f39c1244ba0cf185b2722aeec116b8a98a2ee5728ce687cec0bda60ee0360dfc"},
+    {file = "av-11.0.0.tar.gz", hash = "sha256:48223f000a252070f8e700ff634bb7fb3aa1b7bc7e450373029fbdd6f369ac31"},
+]
+
+[[package]]
+name = "bitarray"
+version = "2.9.2"
+description = "efficient arrays of booleans -- C extension"
+optional = false
+python-versions = "*"
+files = [
+    {file = "bitarray-2.9.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:917905de565d9576eb20f53c797c15ba88b9f4f19728acabec8d01eee1d3756a"},
+    {file = "bitarray-2.9.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:b35bfcb08b7693ab4bf9059111a6e9f14e07d57ac93cd967c420db58ab9b71e1"},
+    {file = "bitarray-2.9.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:ea1923d2e7880f9e1959e035da661767b5a2e16a45dfd57d6aa831e8b65ee1bf"},
+    {file = "bitarray-2.9.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1e0b63a565e8a311cc8348ff1262d5784df0f79d64031d546411afd5dd7ef67d"},
+    {file = "bitarray-2.9.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:cf0620da2b81946d28c0b16f3e3704d38e9837d85ee4f0652816e2609aaa4fed"},
+    {file = "bitarray-2.9.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:79a9b8b05f2876c7195a2b698c47528e86a73c61ea203394ff8e7a4434bda5c8"},
+    {file = "bitarray-2.9.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:345c76b349ff145549652436235c5532e5bfe9db690db6f0a6ad301c62b9ef21"},
+    {file = "bitarray-2.9.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4e2936f090bf3f4d1771f44f9077ebccdbc0415d2b598d51a969afcb519df505"},
+    {file = "bitarray-2.9.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:f9346e98fc2abcef90b942973087e2462af6d3e3710e82938078d3493f7fef52"},
+    {file = "bitarray-2.9.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:e6ec283d4741befb86e8c3ea2e9ac1d17416c956d392107e45263e736954b1f7"},
+    {file = "bitarray-2.9.2-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:962892646599529917ef26266091e4cb3077c88b93c3833a909d68dcc971c4e3"},
+    {file = "bitarray-2.9.2-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:e8da5355d7d75a52df5b84750989e34e39919ec7e59fafc4c104cc1607ab2d31"},
+    {file = "bitarray-2.9.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:603e7d640e54ad764d2b4da6b61e126259af84f253a20f512dd10689566e5478"},
+    {file = "bitarray-2.9.2-cp310-cp310-win32.whl", hash = "sha256:f00079f8e69d75c2a417de7961a77612bb77ef46c09bc74607d86de4740771ef"},
+    {file = "bitarray-2.9.2-cp310-cp310-win_amd64.whl", hash = "sha256:1bb33673e7f7190a65f0a940c1ef63266abdb391f4a3e544a47542d40a81f536"},
+    {file = "bitarray-2.9.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:fe71fd4b76380c2772f96f1e53a524da7063645d647a4fcd3b651bdd80ca0f2e"},
+    {file = "bitarray-2.9.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d527172919cdea1e13994a66d9708a80c3d33dedcf2f0548e4925e600fef3a3a"},
+    {file = "bitarray-2.9.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:052c5073bdcaa9dd10628d99d37a2f33ec09364b86dd1f6281e2d9f8d3db3060"},
+    {file = "bitarray-2.9.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e064caa55a6ed493aca1eda06f8b3f689778bc780a75e6ad7724642ba5dc62f7"},
+    {file = "bitarray-2.9.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:508069a04f658210fdeee85a7a0ca84db4bcc110cbb1d21f692caa13210f24a7"},
+    {file = "bitarray-2.9.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4da73ebd537d75fa7bccfc2228fcaedea0803f21dd9d0bf0d3b67fef3c4af294"},
+    {file = "bitarray-2.9.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5cb378eaa65cd43098f11ff5d27e48ee3b956d2c00d2d6b5bfc2a09fe183be47"},
+    {file = "bitarray-2.9.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d14c790b91f6cbcd9b718f88ed737c78939980c69ac8c7f03dd7e60040c12951"},
+    {file = "bitarray-2.9.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:7eea9318293bc0ea6447e9ebfba600a62f3428bea7e9c6d42170ae4f481dbab3"},
+    {file = "bitarray-2.9.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:b76ffec27c7450b8a334f967366a9ebadaea66ee43f5b530c12861b1a991f503"},
+    {file = "bitarray-2.9.2-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:76b76a07d4ee611405045c6950a1e24c4362b6b44808d4ad6eea75e0dbc59af4"},
+    {file = "bitarray-2.9.2-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:c7d16beeaaab15b075990cd26963d6b5b22e8c5becd131781514a00b8bdd04bd"},
+    {file = "bitarray-2.9.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:60df43e868a615c7e15117a1e1c2e5e11f48f6457280eba6ddf8fbefbec7da99"},
+    {file = "bitarray-2.9.2-cp311-cp311-win32.whl", hash = "sha256:e788608ed7767b7b3bbde6d49058bccdf94df0de9ca75d13aa99020cc7e68095"},
+    {file = "bitarray-2.9.2-cp311-cp311-win_amd64.whl", hash = "sha256:a23397da092ef0a8cfe729571da64c2fc30ac18243caa82ac7c4f965087506ff"},
+    {file = "bitarray-2.9.2-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:90e3a281ffe3897991091b7c46fca38c2675bfd4399ffe79dfeded6c52715436"},
+    {file = "bitarray-2.9.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:bed637b674db5e6c8a97a4a321e3e4d73e72d50b5c6b29950008a93069cc64cd"},
+    {file = "bitarray-2.9.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:e49066d251dbbe4e6e3a5c3937d85b589e40e2669ad0eef41a00f82ec17d844b"},
+    {file = "bitarray-2.9.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3c4344e96642e2211fb3a50558feff682c31563a4c64529a931769d40832ca79"},
+    {file = "bitarray-2.9.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:aeb60962ec4813c539a59fbd4f383509c7222b62c3fb1faa76b54943a613e33a"},
+    {file = "bitarray-2.9.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ed0f7982f10581bb16553719e5e8f933e003f5b22f7d25a68bdb30fac630a6ff"},
+    {file = "bitarray-2.9.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c71d1cabdeee0cdda4669168618f0e46b7dace207b29da7b63aaa1adc2b54081"},
+    {file = "bitarray-2.9.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b0ef2d0a6f1502d38d911d25609b44c6cc27bee0a4363dd295df78b075041b60"},
+    {file = "bitarray-2.9.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:6f71d92f533770fb027388b35b6e11988ab89242b883f48a6fe7202d238c61f8"},
+    {file = "bitarray-2.9.2-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:ba0734aa300757c924f3faf8148e1b8c247176a0ac8e16aefdf9c1eb19e868f7"},
+    {file = "bitarray-2.9.2-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:d91406f413ccbf4af6ab5ae7bc78f772a95609f9ddd14123db36ef8c37116d95"},
+    {file = "bitarray-2.9.2-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:87abb7f80c0a042f3fe8e5264da1a2756267450bb602110d5327b8eaff7682e7"},
+    {file = "bitarray-2.9.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:4b558ce85579b51a2e38703877d1e93b7728a7af664dd45a34e833534f0b755d"},
+    {file = "bitarray-2.9.2-cp312-cp312-win32.whl", hash = "sha256:dac2399ee2889fbdd3472bfc2ede74c34cceb1ccf29a339964281a16eb1d3188"},
+    {file = "bitarray-2.9.2-cp312-cp312-win_amd64.whl", hash = "sha256:48a30d718d1a6dfc22a49547450107abe8f4afdf2abdcbe76eb9ed88edc49498"},
+    {file = "bitarray-2.9.2-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:2c6be1b651fad8f3adb7a5aa12c65b612cd9b89530969af941844ae680f7d981"},
+    {file = "bitarray-2.9.2-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c5b399ae6ab975257ec359f03b48fc00b1c1cd109471e41903548469b8feae5c"},
+    {file = "bitarray-2.9.2-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0b3543c8a1cb286ad105f11c25d8d0f712f41c5c55f90be39f0e5a1376c7d0b0"},
+    {file = "bitarray-2.9.2-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:03adaacb79e2fb8f483ab3a67665eec53bb3fd0cd5dbd7358741aef124688db3"},
+    {file = "bitarray-2.9.2-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9ae5b0657380d2581e13e46864d147a52c1e2bbac9f59b59c576e42fa7d10cf0"},
+    {file = "bitarray-2.9.2-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7c1f4bf6ea8eb9d7f30808c2e9894237a96650adfecbf5f3643862dc5982f89e"},
+    {file = "bitarray-2.9.2-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:a8873089be2aa15494c0f81af1209f6e1237d762c5065bc4766c1b84321e1b50"},
+    {file = "bitarray-2.9.2-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:677e67f50e2559efc677a4366707070933ad5418b8347a603a49a070890b19bc"},
+    {file = "bitarray-2.9.2-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:a620d8ce4ea2f1c73c6b6b1399e14cb68c6915e2be3fad5808c2998ed55b4acf"},
+    {file = "bitarray-2.9.2-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:64115ccabbdbe279c24c367b629c6b1d3da9ed36c7420129e27c338a3971bfee"},
+    {file = "bitarray-2.9.2-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:5d6fb422772e75385b76ad1c52f45a68bd4efafd8be8d0061c11877be74c4d43"},
+    {file = "bitarray-2.9.2-cp36-cp36m-win32.whl", hash = "sha256:852e202875dd6dfd6139ce7ec4e98dac2b17d8d25934dc99900831e81c3adaef"},
+    {file = "bitarray-2.9.2-cp36-cp36m-win_amd64.whl", hash = "sha256:7dfefdcb0dc6a3ba9936063cec65a74595571b375beabe18742b3d91d087eefd"},
+    {file = "bitarray-2.9.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:b306c4cf66912511422060f7f5e1149c8bdb404f8e00e600561b0749fdd45659"},
+    {file = "bitarray-2.9.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a09c4f81635408e3387348f415521d4b94198c562c23330f560596a6aaa26eaf"},
+    {file = "bitarray-2.9.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5361413fd2ecfdf44dc8f065177dc6aba97fa80a91b815586cb388763acf7f8d"},
+    {file = "bitarray-2.9.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e8a9475d415ef1eaae7942df6f780fa4dcd48fce32825eda591a17abba869299"},
+    {file = "bitarray-2.9.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c9b87baa7bfff9a5878fcc1bffe49ecde6e647a72a64b39a69cd8a2992a43a34"},
+    {file = "bitarray-2.9.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bb6b86cfdfc503e92cb71c68766a24565359136961642504a7cc9faf936d9c88"},
+    {file = "bitarray-2.9.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:cd56b8ae87ebc71bcacbd73615098e8a8de952ecbb5785b6b4e2b07da8a06e1f"},
+    {file = "bitarray-2.9.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:3fa909cfd675004aed8b4cc9df352415933656e0155a6209d878b7cb615c787e"},
+    {file = "bitarray-2.9.2-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:b069ca9bf728e0c5c5b60e00a89df9af34cc170c695c3bfa3b372d8f40288efb"},
+    {file = "bitarray-2.9.2-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:6067f2f07a7121749858c7daa93c8774325c91590b3e81a299621e347740c2ae"},
+    {file = "bitarray-2.9.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:321841cdad1dd0f58fe62e80e9c9c7531f8ebf8be93f047401e930dc47425b1e"},
+    {file = "bitarray-2.9.2-cp37-cp37m-win32.whl", hash = "sha256:54e16e32e60973bb83c315de9975bc1bcfc9bd50bb13001c31da159bc49b0ca1"},
+    {file = "bitarray-2.9.2-cp37-cp37m-win_amd64.whl", hash = "sha256:f4dcadb7b8034aa3491ee8f5a69b3d9ba9d7d1e55c3cc1fc45be313e708277f8"},
+    {file = "bitarray-2.9.2-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:c8919fdbd3bb596b104388b56ae4b266eb28da1f2f7dff2e1f9334a21840fe96"},
+    {file = "bitarray-2.9.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:eb7a9d8a2e400a1026de341ad48e21670a6261a75b06df162c5c39b0d0e7c8f4"},
+    {file = "bitarray-2.9.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:6ec84668dd7b937874a2b2c293cd14ba84f37be0d196dead852e0ada9815d807"},
+    {file = "bitarray-2.9.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f2de9a31c34e543ae089fd2a5ced01292f725190e379921384f695e2d7184bd3"},
+    {file = "bitarray-2.9.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9521f49ae121a17c0a41e5112249e6fa7f6a571245b1118de81fb86e7c1bc1ce"},
+    {file = "bitarray-2.9.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a6cc6545d6d76542aee3d18c1c9485fb7b9812b8df4ebe52c4535ec42081b48f"},
+    {file = "bitarray-2.9.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:856bbe1616425f71c0df5ef2e8755e878d9504d5a531acba58ab4273c52c117a"},
+    {file = "bitarray-2.9.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d4bba8042ea6ab331ade91bc435d81ad72fddb098e49108610b0ce7780c14e68"},
+    {file = "bitarray-2.9.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:a035da89c959d98afc813e3c62f052690d67cfd55a36592f25d734b70de7d4b0"},
+    {file = "bitarray-2.9.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:6d70b1579da7fb71be5a841a1f965d19aca0ef27f629cfc07d06b09aafd0a333"},
+    {file = "bitarray-2.9.2-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:405b83bed28efaae6d86b6ab287c75712ead0adbfab2a1075a1b7ab47dad4d62"},
+    {file = "bitarray-2.9.2-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:7eb8be687c50da0b397d5e0ab7ca200b5ebb639e79a9f5e285851d1944c94be9"},
+    {file = "bitarray-2.9.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:eceb551dfeaf19c609003a69a0cf8264b0efd7abc3791a11dfabf4788daf0d19"},
+    {file = "bitarray-2.9.2-cp38-cp38-win32.whl", hash = "sha256:bb198c6ed1edbcdaf3d1fa3c9c9d1cdb7e179a5134ef5ee660b53cdec43b34e7"},
+    {file = "bitarray-2.9.2-cp38-cp38-win_amd64.whl", hash = "sha256:648d2f2685590b0103c67a937c2fb9e09bcc8dfb166f0c7c77bd341902a6f5b3"},
+    {file = "bitarray-2.9.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:ea816dc8f8e65841a8bbdd30e921edffeeb6f76efe6a1eb0da147b60d539d1cf"},
+    {file = "bitarray-2.9.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:4d0e32530f941c41eddfc77600ec89b65184cb909c549336463a738fab3ed285"},
+    {file = "bitarray-2.9.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4a22266fb416a3b6c258bf7f83c9fe531ba0b755a56986a81ad69dc0f3bcc070"},
+    {file = "bitarray-2.9.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fc6d3e80dd8239850f2604833ff3168b28909c8a9357abfed95632cccd17e3e7"},
+    {file = "bitarray-2.9.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f135e804986b12bf14f2cd1eb86674c47dea86c4c5f0fa13c88978876b97ebe6"},
+    {file = "bitarray-2.9.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:87580c7f7d14f7ec401eda7adac1e2a25e95153e9c339872c8ae61b3208819a1"},
+    {file = "bitarray-2.9.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:64b433e26993127732ac7b66a7821b2537c3044355798de7c5fcb0af34b8296f"},
+    {file = "bitarray-2.9.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1e497c535f2a9b68c69d36631bf2dba243e05eb343b00b9c7bbdc8c601c6802d"},
+    {file = "bitarray-2.9.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:e40b3cb9fa1edb4e0175d7c06345c49c7925fe93e39ef55ecb0bc40c906b0c09"},
+    {file = "bitarray-2.9.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:f2f8692f95c9e377eb19ca519d30d1f884b02feb7e115f798de47570a359e43f"},
+    {file = "bitarray-2.9.2-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:f0b84fc50b6dbeced4fa390688c07c10a73222810fb0e08392bd1a1b8259de36"},
+    {file = "bitarray-2.9.2-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:d656ad38c942e38a470ddbce26b5020e08e1a7ea86b8fd413bb9024b5189993a"},
+    {file = "bitarray-2.9.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:6ab0f1dbfe5070db98771a56aa14797595acd45a1af9eadfb193851a270e7996"},
+    {file = "bitarray-2.9.2-cp39-cp39-win32.whl", hash = "sha256:0a99b23ac845a9ea3157782c97465e6ae026fe0c7c4c1ed1d88f759fd6ea52d9"},
+    {file = "bitarray-2.9.2-cp39-cp39-win_amd64.whl", hash = "sha256:9bbcfc7c279e8d74b076e514e669b683f77b4a2a328585b3f16d4c5259c91222"},
+    {file = "bitarray-2.9.2-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:43847799461d8ba71deb4d97b47250c2c2fb66d82cd3cb8b4caf52bb97c03034"},
+    {file = "bitarray-2.9.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f4f44381b0a4bdf64416082f4f0e7140377ae962c0ced6f983c6d7bbfc034040"},
+    {file = "bitarray-2.9.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a484061616fb4b158b80789bd3cb511f399d2116525a8b29b6334c68abc2310f"},
+    {file = "bitarray-2.9.2-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1ff9e38356cc803e06134cf8ae9758e836ccd1b793135ef3db53c7c5d71e93bc"},
+    {file = "bitarray-2.9.2-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:b44105792fbdcfbda3e26ee88786790fda409da4c71f6c2b73888108cf8f062f"},
+    {file = "bitarray-2.9.2-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:7e913098de169c7fc890638ce5e171387363eb812579e637c44261460ac00aa2"},
+    {file = "bitarray-2.9.2-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d6fe315355cdfe3ed22ef355b8bdc81a805ca4d0949d921576560e5b227a1112"},
+    {file = "bitarray-2.9.2-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f708e91fdbe443f3bec2df394ed42328fb9b0446dff5cb4199023ac6499e09fd"},
+    {file = "bitarray-2.9.2-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5b7b09489b71f9f1f64c0fa0977e250ec24500767dab7383ba9912495849cadf"},
+    {file = "bitarray-2.9.2-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:128cc3488176145b9b137fdcf54c1c201809bbb8dd30b260ee40afe915843b43"},
+    {file = "bitarray-2.9.2-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:21f21e7f56206be346bdbda2a6bdb2165a5e6a11821f88fd4911c5a6bbbdc7e2"},
+    {file = "bitarray-2.9.2-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5f4dd3af86dd8a617eb6464622fb64ca86e61ce99b59b5c35d8cd33f9c30603d"},
+    {file = "bitarray-2.9.2-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6465de861aff7a2559f226b37982007417eab8c3557543879987f58b453519bd"},
+    {file = "bitarray-2.9.2-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:dbaf2bb71d6027152d603f1d5f31e0dfd5e50173d06f877bec484e5396d4594b"},
+    {file = "bitarray-2.9.2-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:2f32948c86e0d230a296686db28191b67ed229756f84728847daa0c7ab7406e3"},
+    {file = "bitarray-2.9.2-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:be94e5a685e60f9d24532af8fe5c268002e9016fa80272a94727f435de3d1003"},
+    {file = "bitarray-2.9.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a5cc9381fd54f3c23ae1039f977bfd6d041a5c3c1518104f616643c3a5a73b15"},
+    {file = "bitarray-2.9.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cd926e8ae4d1ed1ac4a8f37212a62886292f692bc1739fde98013bf210c2d175"},
+    {file = "bitarray-2.9.2-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:461a3dafb9d5fda0bb3385dc507d78b1984b49da3fe4c6d56c869a54373b7008"},
+    {file = "bitarray-2.9.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:393cb27fd859af5fd9c16eb26b1c59b17b390ff66b3ae5d0dd258270191baf13"},
+    {file = "bitarray-2.9.2.tar.gz", hash = "sha256:a8f286a51a32323715d77755ed959f94bef13972e9a2fe71b609e40e6d27957e"},
+]
+
+[[package]]
+name = "certifi"
+version = "2023.11.17"
+description = "Python package for providing Mozilla's CA Bundle."
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "certifi-2023.11.17-py3-none-any.whl", hash = "sha256:e036ab49d5b79556f99cfc2d9320b34cfbe5be05c5871b51de9329f0603b0474"},
+    {file = "certifi-2023.11.17.tar.gz", hash = "sha256:9b469f3a900bf28dc19b8cfbf8019bf47f7fdd1a65a1d4ffb98fc14166beb4d1"},
+]
+
+[[package]]
+name = "cffi"
+version = "1.16.0"
+description = "Foreign Function Interface for Python calling C code."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "cffi-1.16.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:6b3d6606d369fc1da4fd8c357d026317fbb9c9b75d36dc16e90e84c26854b088"},
+    {file = "cffi-1.16.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:ac0f5edd2360eea2f1daa9e26a41db02dd4b0451b48f7c318e217ee092a213e9"},
+    {file = "cffi-1.16.0-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7e61e3e4fa664a8588aa25c883eab612a188c725755afff6289454d6362b9673"},
+    {file = "cffi-1.16.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a72e8961a86d19bdb45851d8f1f08b041ea37d2bd8d4fd19903bc3083d80c896"},
+    {file = "cffi-1.16.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5b50bf3f55561dac5438f8e70bfcdfd74543fd60df5fa5f62d94e5867deca684"},
+    {file = "cffi-1.16.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7651c50c8c5ef7bdb41108b7b8c5a83013bfaa8a935590c5d74627c047a583c7"},
+    {file = "cffi-1.16.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e4108df7fe9b707191e55f33efbcb2d81928e10cea45527879a4749cbe472614"},
+    {file = "cffi-1.16.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:32c68ef735dbe5857c810328cb2481e24722a59a2003018885514d4c09af9743"},
+    {file = "cffi-1.16.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:673739cb539f8cdaa07d92d02efa93c9ccf87e345b9a0b556e3ecc666718468d"},
+    {file = "cffi-1.16.0-cp310-cp310-win32.whl", hash = "sha256:9f90389693731ff1f659e55c7d1640e2ec43ff725cc61b04b2f9c6d8d017df6a"},
+    {file = "cffi-1.16.0-cp310-cp310-win_amd64.whl", hash = "sha256:e6024675e67af929088fda399b2094574609396b1decb609c55fa58b028a32a1"},
+    {file = "cffi-1.16.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b84834d0cf97e7d27dd5b7f3aca7b6e9263c56308ab9dc8aae9784abb774d404"},
+    {file = "cffi-1.16.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:1b8ebc27c014c59692bb2664c7d13ce7a6e9a629be20e54e7271fa696ff2b417"},
+    {file = "cffi-1.16.0-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ee07e47c12890ef248766a6e55bd38ebfb2bb8edd4142d56db91b21ea68b7627"},
+    {file = "cffi-1.16.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d8a9d3ebe49f084ad71f9269834ceccbf398253c9fac910c4fd7053ff1386936"},
+    {file = "cffi-1.16.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e70f54f1796669ef691ca07d046cd81a29cb4deb1e5f942003f401c0c4a2695d"},
+    {file = "cffi-1.16.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5bf44d66cdf9e893637896c7faa22298baebcd18d1ddb6d2626a6e39793a1d56"},
+    {file = "cffi-1.16.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7b78010e7b97fef4bee1e896df8a4bbb6712b7f05b7ef630f9d1da00f6444d2e"},
+    {file = "cffi-1.16.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:c6a164aa47843fb1b01e941d385aab7215563bb8816d80ff3a363a9f8448a8dc"},
+    {file = "cffi-1.16.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e09f3ff613345df5e8c3667da1d918f9149bd623cd9070c983c013792a9a62eb"},
+    {file = "cffi-1.16.0-cp311-cp311-win32.whl", hash = "sha256:2c56b361916f390cd758a57f2e16233eb4f64bcbeee88a4881ea90fca14dc6ab"},
+    {file = "cffi-1.16.0-cp311-cp311-win_amd64.whl", hash = "sha256:db8e577c19c0fda0beb7e0d4e09e0ba74b1e4c092e0e40bfa12fe05b6f6d75ba"},
+    {file = "cffi-1.16.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:fa3a0128b152627161ce47201262d3140edb5a5c3da88d73a1b790a959126956"},
+    {file = "cffi-1.16.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:68e7c44931cc171c54ccb702482e9fc723192e88d25a0e133edd7aff8fcd1f6e"},
+    {file = "cffi-1.16.0-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:abd808f9c129ba2beda4cfc53bde801e5bcf9d6e0f22f095e45327c038bfe68e"},
+    {file = "cffi-1.16.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:88e2b3c14bdb32e440be531ade29d3c50a1a59cd4e51b1dd8b0865c54ea5d2e2"},
+    {file = "cffi-1.16.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:fcc8eb6d5902bb1cf6dc4f187ee3ea80a1eba0a89aba40a5cb20a5087d961357"},
+    {file = "cffi-1.16.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b7be2d771cdba2942e13215c4e340bfd76398e9227ad10402a8767ab1865d2e6"},
+    {file = "cffi-1.16.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e715596e683d2ce000574bae5d07bd522c781a822866c20495e52520564f0969"},
+    {file = "cffi-1.16.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:2d92b25dbf6cae33f65005baf472d2c245c050b1ce709cc4588cdcdd5495b520"},
+    {file = "cffi-1.16.0-cp312-cp312-win32.whl", hash = "sha256:b2ca4e77f9f47c55c194982e10f058db063937845bb2b7a86c84a6cfe0aefa8b"},
+    {file = "cffi-1.16.0-cp312-cp312-win_amd64.whl", hash = "sha256:68678abf380b42ce21a5f2abde8efee05c114c2fdb2e9eef2efdb0257fba1235"},
+    {file = "cffi-1.16.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:0c9ef6ff37e974b73c25eecc13952c55bceed9112be2d9d938ded8e856138bcc"},
+    {file = "cffi-1.16.0-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a09582f178759ee8128d9270cd1344154fd473bb77d94ce0aeb2a93ebf0feaf0"},
+    {file = "cffi-1.16.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e760191dd42581e023a68b758769e2da259b5d52e3103c6060ddc02c9edb8d7b"},
+    {file = "cffi-1.16.0-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:80876338e19c951fdfed6198e70bc88f1c9758b94578d5a7c4c91a87af3cf31c"},
+    {file = "cffi-1.16.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a6a14b17d7e17fa0d207ac08642c8820f84f25ce17a442fd15e27ea18d67c59b"},
+    {file = "cffi-1.16.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6602bc8dc6f3a9e02b6c22c4fc1e47aa50f8f8e6d3f78a5e16ac33ef5fefa324"},
+    {file = "cffi-1.16.0-cp38-cp38-win32.whl", hash = "sha256:131fd094d1065b19540c3d72594260f118b231090295d8c34e19a7bbcf2e860a"},
+    {file = "cffi-1.16.0-cp38-cp38-win_amd64.whl", hash = "sha256:31d13b0f99e0836b7ff893d37af07366ebc90b678b6664c955b54561fc36ef36"},
+    {file = "cffi-1.16.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:582215a0e9adbe0e379761260553ba11c58943e4bbe9c36430c4ca6ac74b15ed"},
+    {file = "cffi-1.16.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:b29ebffcf550f9da55bec9e02ad430c992a87e5f512cd63388abb76f1036d8d2"},
+    {file = "cffi-1.16.0-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:dc9b18bf40cc75f66f40a7379f6a9513244fe33c0e8aa72e2d56b0196a7ef872"},
+    {file = "cffi-1.16.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9cb4a35b3642fc5c005a6755a5d17c6c8b6bcb6981baf81cea8bfbc8903e8ba8"},
+    {file = "cffi-1.16.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b86851a328eedc692acf81fb05444bdf1891747c25af7529e39ddafaf68a4f3f"},
+    {file = "cffi-1.16.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c0f31130ebc2d37cdd8e44605fb5fa7ad59049298b3f745c74fa74c62fbfcfc4"},
+    {file = "cffi-1.16.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8f8e709127c6c77446a8c0a8c8bf3c8ee706a06cd44b1e827c3e6a2ee6b8c098"},
+    {file = "cffi-1.16.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:748dcd1e3d3d7cd5443ef03ce8685043294ad6bd7c02a38d1bd367cfd968e000"},
+    {file = "cffi-1.16.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:8895613bcc094d4a1b2dbe179d88d7fb4a15cee43c052e8885783fac397d91fe"},
+    {file = "cffi-1.16.0-cp39-cp39-win32.whl", hash = "sha256:ed86a35631f7bfbb28e108dd96773b9d5a6ce4811cf6ea468bb6a359b256b1e4"},
+    {file = "cffi-1.16.0-cp39-cp39-win_amd64.whl", hash = "sha256:3686dffb02459559c74dd3d81748269ffb0eb027c39a6fc99502de37d501faa8"},
+    {file = "cffi-1.16.0.tar.gz", hash = "sha256:bcb3ef43e58665bbda2fb198698fcae6776483e0c4a631aa5647806c25e02cc0"},
+]
+
+[package.dependencies]
+pycparser = "*"
+
+[[package]]
+name = "charset-normalizer"
+version = "3.3.2"
+description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
+optional = false
+python-versions = ">=3.7.0"
+files = [
+    {file = "charset-normalizer-3.3.2.tar.gz", hash = "sha256:f30c3cb33b24454a82faecaf01b19c18562b1e89558fb6c56de4d9118a032fd5"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:25baf083bf6f6b341f4121c2f3c548875ee6f5339300e08be3f2b2ba1721cdd3"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:06435b539f889b1f6f4ac1758871aae42dc3a8c0e24ac9e60c2384973ad73027"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9063e24fdb1e498ab71cb7419e24622516c4a04476b17a2dab57e8baa30d6e03"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6897af51655e3691ff853668779c7bad41579facacf5fd7253b0133308cf000d"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1d3193f4a680c64b4b6a9115943538edb896edc190f0b222e73761716519268e"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cd70574b12bb8a4d2aaa0094515df2463cb429d8536cfb6c7ce983246983e5a6"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8465322196c8b4d7ab6d1e049e4c5cb460d0394da4a27d23cc242fbf0034b6b5"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a9a8e9031d613fd2009c182b69c7b2c1ef8239a0efb1df3f7c8da66d5dd3d537"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:beb58fe5cdb101e3a055192ac291b7a21e3b7ef4f67fa1d74e331a7f2124341c"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:e06ed3eb3218bc64786f7db41917d4e686cc4856944f53d5bdf83a6884432e12"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:2e81c7b9c8979ce92ed306c249d46894776a909505d8f5a4ba55b14206e3222f"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:572c3763a264ba47b3cf708a44ce965d98555f618ca42c926a9c1616d8f34269"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:fd1abc0d89e30cc4e02e4064dc67fcc51bd941eb395c502aac3ec19fab46b519"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-win32.whl", hash = "sha256:3d47fa203a7bd9c5b6cee4736ee84ca03b8ef23193c0d1ca99b5089f72645c73"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-win_amd64.whl", hash = "sha256:10955842570876604d404661fbccbc9c7e684caf432c09c715ec38fbae45ae09"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:802fe99cca7457642125a8a88a084cef28ff0cf9407060f7b93dca5aa25480db"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:573f6eac48f4769d667c4442081b1794f52919e7edada77495aaed9236d13a96"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:549a3a73da901d5bc3ce8d24e0600d1fa85524c10287f6004fbab87672bf3e1e"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f27273b60488abe721a075bcca6d7f3964f9f6f067c8c4c605743023d7d3944f"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1ceae2f17a9c33cb48e3263960dc5fc8005351ee19db217e9b1bb15d28c02574"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:65f6f63034100ead094b8744b3b97965785388f308a64cf8d7c34f2f2e5be0c4"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:753f10e867343b4511128c6ed8c82f7bec3bd026875576dfd88483c5c73b2fd8"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4a78b2b446bd7c934f5dcedc588903fb2f5eec172f3d29e52a9096a43722adfc"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:e537484df0d8f426ce2afb2d0f8e1c3d0b114b83f8850e5f2fbea0e797bd82ae"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:eb6904c354526e758fda7167b33005998fb68c46fbc10e013ca97f21ca5c8887"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:deb6be0ac38ece9ba87dea880e438f25ca3eddfac8b002a2ec3d9183a454e8ae"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:4ab2fe47fae9e0f9dee8c04187ce5d09f48eabe611be8259444906793ab7cbce"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:80402cd6ee291dcb72644d6eac93785fe2c8b9cb30893c1af5b8fdd753b9d40f"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-win32.whl", hash = "sha256:7cd13a2e3ddeed6913a65e66e94b51d80a041145a026c27e6bb76c31a853c6ab"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-win_amd64.whl", hash = "sha256:663946639d296df6a2bb2aa51b60a2454ca1cb29835324c640dafb5ff2131a77"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:0b2b64d2bb6d3fb9112bafa732def486049e63de9618b5843bcdd081d8144cd8"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:ddbb2551d7e0102e7252db79ba445cdab71b26640817ab1e3e3648dad515003b"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:55086ee1064215781fff39a1af09518bc9255b50d6333f2e4c74ca09fac6a8f6"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8f4a014bc36d3c57402e2977dada34f9c12300af536839dc38c0beab8878f38a"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a10af20b82360ab00827f916a6058451b723b4e65030c5a18577c8b2de5b3389"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8d756e44e94489e49571086ef83b2bb8ce311e730092d2c34ca8f7d925cb20aa"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:90d558489962fd4918143277a773316e56c72da56ec7aa3dc3dbbe20fdfed15b"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6ac7ffc7ad6d040517be39eb591cac5ff87416c2537df6ba3cba3bae290c0fed"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:7ed9e526742851e8d5cc9e6cf41427dfc6068d4f5a3bb03659444b4cabf6bc26"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:8bdb58ff7ba23002a4c5808d608e4e6c687175724f54a5dade5fa8c67b604e4d"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:6b3251890fff30ee142c44144871185dbe13b11bab478a88887a639655be1068"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:b4a23f61ce87adf89be746c8a8974fe1c823c891d8f86eb218bb957c924bb143"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:efcb3f6676480691518c177e3b465bcddf57cea040302f9f4e6e191af91174d4"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-win32.whl", hash = "sha256:d965bba47ddeec8cd560687584e88cf699fd28f192ceb452d1d7ee807c5597b7"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-win_amd64.whl", hash = "sha256:96b02a3dc4381e5494fad39be677abcb5e6634bf7b4fa83a6dd3112607547001"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:95f2a5796329323b8f0512e09dbb7a1860c46a39da62ecb2324f116fa8fdc85c"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c002b4ffc0be611f0d9da932eb0f704fe2602a9a949d1f738e4c34c75b0863d5"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a981a536974bbc7a512cf44ed14938cf01030a99e9b3a06dd59578882f06f985"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3287761bc4ee9e33561a7e058c72ac0938c4f57fe49a09eae428fd88aafe7bb6"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:42cb296636fcc8b0644486d15c12376cb9fa75443e00fb25de0b8602e64c1714"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0a55554a2fa0d408816b3b5cedf0045f4b8e1a6065aec45849de2d6f3f8e9786"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:c083af607d2515612056a31f0a8d9e0fcb5876b7bfc0abad3ecd275bc4ebc2d5"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:87d1351268731db79e0f8e745d92493ee2841c974128ef629dc518b937d9194c"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:bd8f7df7d12c2db9fab40bdd87a7c09b1530128315d047a086fa3ae3435cb3a8"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:c180f51afb394e165eafe4ac2936a14bee3eb10debc9d9e4db8958fe36afe711"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:8c622a5fe39a48f78944a87d4fb8a53ee07344641b0562c540d840748571b811"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-win32.whl", hash = "sha256:db364eca23f876da6f9e16c9da0df51aa4f104a972735574842618b8c6d999d4"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-win_amd64.whl", hash = "sha256:86216b5cee4b06df986d214f664305142d9c76df9b6512be2738aa72a2048f99"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:6463effa3186ea09411d50efc7d85360b38d5f09b870c48e4600f63af490e56a"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:6c4caeef8fa63d06bd437cd4bdcf3ffefe6738fb1b25951440d80dc7df8c03ac"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:37e55c8e51c236f95b033f6fb391d7d7970ba5fe7ff453dad675e88cf303377a"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fb69256e180cb6c8a894fee62b3afebae785babc1ee98b81cdf68bbca1987f33"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ae5f4161f18c61806f411a13b0310bea87f987c7d2ecdbdaad0e94eb2e404238"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b2b0a0c0517616b6869869f8c581d4eb2dd83a4d79e0ebcb7d373ef9956aeb0a"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:45485e01ff4d3630ec0d9617310448a8702f70e9c01906b0d0118bdf9d124cf2"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:eb00ed941194665c332bf8e078baf037d6c35d7c4f3102ea2d4f16ca94a26dc8"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:2127566c664442652f024c837091890cb1942c30937add288223dc895793f898"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:a50aebfa173e157099939b17f18600f72f84eed3049e743b68ad15bd69b6bf99"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:4d0d1650369165a14e14e1e47b372cfcb31d6ab44e6e33cb2d4e57265290044d"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:923c0c831b7cfcb071580d3f46c4baf50f174be571576556269530f4bbd79d04"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:06a81e93cd441c56a9b65d8e1d043daeb97a3d0856d177d5c90ba85acb3db087"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-win32.whl", hash = "sha256:6ef1d82a3af9d3eecdba2321dc1b3c238245d890843e040e41e470ffa64c3e25"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-win_amd64.whl", hash = "sha256:eb8821e09e916165e160797a6c17edda0679379a4be5c716c260e836e122f54b"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:c235ebd9baae02f1b77bcea61bce332cb4331dc3617d254df3323aa01ab47bd4"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:5b4c145409bef602a690e7cfad0a15a55c13320ff7a3ad7ca59c13bb8ba4d45d"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:68d1f8a9e9e37c1223b656399be5d6b448dea850bed7d0f87a8311f1ff3dabb0"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:22afcb9f253dac0696b5a4be4a1c0f8762f8239e21b99680099abd9b2b1b2269"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e27ad930a842b4c5eb8ac0016b0a54f5aebbe679340c26101df33424142c143c"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1f79682fbe303db92bc2b1136016a38a42e835d932bab5b3b1bfcfbf0640e519"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b261ccdec7821281dade748d088bb6e9b69e6d15b30652b74cbbac25e280b796"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:122c7fa62b130ed55f8f285bfd56d5f4b4a5b503609d181f9ad85e55c89f4185"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:d0eccceffcb53201b5bfebb52600a5fb483a20b61da9dbc885f8b103cbe7598c"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:9f96df6923e21816da7e0ad3fd47dd8f94b2a5ce594e00677c0013018b813458"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:7f04c839ed0b6b98b1a7501a002144b76c18fb1c1850c8b98d458ac269e26ed2"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:34d1c8da1e78d2e001f363791c98a272bb734000fcef47a491c1e3b0505657a8"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:ff8fa367d09b717b2a17a052544193ad76cd49979c805768879cb63d9ca50561"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-win32.whl", hash = "sha256:aed38f6e4fb3f5d6bf81bfa990a07806be9d83cf7bacef998ab1a9bd660a581f"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-win_amd64.whl", hash = "sha256:b01b88d45a6fcb69667cd6d2f7a9aeb4bf53760d7fc536bf679ec94fe9f3ff3d"},
+    {file = "charset_normalizer-3.3.2-py3-none-any.whl", hash = "sha256:3e4d1f6587322d2788836a99c69062fbb091331ec940e02d12d179c1d53e25fc"},
+]
+
+[[package]]
+name = "click"
+version = "8.1.7"
+description = "Composable command line interface toolkit"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "click-8.1.7-py3-none-any.whl", hash = "sha256:ae74fb96c20a0277a1d615f1e4d73c8414f5a98db8b799a7931d1582f3390c28"},
+    {file = "click-8.1.7.tar.gz", hash = "sha256:ca9853ad459e787e2192211578cc907e7594e294c7ccc834310722b41b9ca6de"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
+[[package]]
+name = "colorama"
+version = "0.4.6"
+description = "Cross-platform colored terminal text."
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
+files = [
+    {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
+    {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
+]
+
+[[package]]
+name = "cython"
+version = "3.0.8"
+description = "The Cython compiler for writing C extensions in the Python language."
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+files = [
+    {file = "Cython-3.0.8-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:a846e0a38e2b24e9a5c5dc74b0e54c6e29420d88d1dafabc99e0fc0f3e338636"},
+    {file = "Cython-3.0.8-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:45523fdc2b78d79b32834cc1cc12dc2ca8967af87e22a3ee1bff20e77c7f5520"},
+    {file = "Cython-3.0.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:baa0b7f3f841fe087410cab66778e2d3fb20ae2d2078a2be3dffe66c6574be39"},
+    {file = "Cython-3.0.8-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e87294e33e40c289c77a135f491cd721bd089f193f956f7b8ed5aa2d0b8c558f"},
+    {file = "Cython-3.0.8-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:a1df7a129344b1215c20096d33c00193437df1a8fcca25b71f17c23b1a44f782"},
+    {file = "Cython-3.0.8-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:13c2a5e57a0358da467d97667297bf820b62a1a87ae47c5f87938b9bb593acbd"},
+    {file = "Cython-3.0.8-cp310-cp310-win32.whl", hash = "sha256:96b028f044f5880e3cb18ecdcfc6c8d3ce9d0af28418d5ab464509f26d8adf12"},
+    {file = "Cython-3.0.8-cp310-cp310-win_amd64.whl", hash = "sha256:8140597a8b5cc4f119a1190f5a2228a84f5ca6d8d9ec386cfce24663f48b2539"},
+    {file = "Cython-3.0.8-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:aae26f9663e50caf9657148403d9874eea41770ecdd6caf381d177c2b1bb82ba"},
+    {file = "Cython-3.0.8-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:547eb3cdb2f8c6f48e6865d5a741d9dd051c25b3ce076fbca571727977b28ac3"},
+    {file = "Cython-3.0.8-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5a567d4b9ba70b26db89d75b243529de9e649a2f56384287533cf91512705bee"},
+    {file = "Cython-3.0.8-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:51d1426263b0e82fb22bda8ea60dc77a428581cc19e97741011b938445d383f1"},
+    {file = "Cython-3.0.8-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:c26daaeccda072459b48d211415fd1e5507c06bcd976fa0d5b8b9f1063467d7b"},
+    {file = "Cython-3.0.8-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:289ce7838208211cd166e975865fd73b0649bf118170b6cebaedfbdaf4a37795"},
+    {file = "Cython-3.0.8-cp311-cp311-win32.whl", hash = "sha256:c8aa05f5e17f8042a3be052c24f2edc013fb8af874b0bf76907d16c51b4e7871"},
+    {file = "Cython-3.0.8-cp311-cp311-win_amd64.whl", hash = "sha256:000dc9e135d0eec6ecb2b40a5b02d0868a2f8d2e027a41b0fe16a908a9e6de02"},
+    {file = "Cython-3.0.8-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:90d3fe31db55685d8cb97d43b0ec39ef614fcf660f83c77ed06aa670cb0e164f"},
+    {file = "Cython-3.0.8-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e24791ddae2324e88e3c902a765595c738f19ae34ee66bfb1a6dac54b1833419"},
+    {file = "Cython-3.0.8-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2f020fa1c0552052e0660790b8153b79e3fc9a15dbd8f1d0b841fe5d204a6ae6"},
+    {file = "Cython-3.0.8-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:18bfa387d7a7f77d7b2526af69a65dbd0b731b8d941aaff5becff8e21f6d7717"},
+    {file = "Cython-3.0.8-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:fe81b339cffd87c0069c6049b4d33e28bdd1874625ee515785bf42c9fdff3658"},
+    {file = "Cython-3.0.8-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:80fd94c076e1e1b1ee40a309be03080b75f413e8997cddcf401a118879863388"},
+    {file = "Cython-3.0.8-cp312-cp312-win32.whl", hash = "sha256:85077915a93e359a9b920280d214dc0cf8a62773e1f3d7d30fab8ea4daed670c"},
+    {file = "Cython-3.0.8-cp312-cp312-win_amd64.whl", hash = "sha256:0cb2dcc565c7851f75d496f724a384a790fab12d1b82461b663e66605bec429a"},
+    {file = "Cython-3.0.8-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:870d2a0a7e3cbd5efa65aecdb38d715ea337a904ea7bb22324036e78fb7068e7"},
+    {file = "Cython-3.0.8-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7e8f2454128974905258d86534f4fd4f91d2f1343605657ecab779d80c9d6d5e"},
+    {file = "Cython-3.0.8-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c1949d6aa7bc792554bee2b67a9fe41008acbfe22f4f8df7b6ec7b799613a4b3"},
+    {file = "Cython-3.0.8-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c9f2c6e1b8f3bcd6cb230bac1843f85114780bb8be8614855b1628b36bb510e0"},
+    {file = "Cython-3.0.8-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:05d7eddc668ae7993643f32c7661f25544e791edb745758672ea5b1a82ecffa6"},
+    {file = "Cython-3.0.8-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:bfabe115deef4ada5d23c87bddb11289123336dcc14347011832c07db616dd93"},
+    {file = "Cython-3.0.8-cp36-cp36m-win32.whl", hash = "sha256:0c38c9f0bcce2df0c3347285863621be904ac6b64c5792d871130569d893efd7"},
+    {file = "Cython-3.0.8-cp36-cp36m-win_amd64.whl", hash = "sha256:6c46939c3983217d140999de7c238c3141f56b1ea349e47ca49cae899969aa2c"},
+    {file = "Cython-3.0.8-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:115f0a50f752da6c99941b103b5cb090da63eb206abbc7c2ad33856ffc73f064"},
+    {file = "Cython-3.0.8-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c9c0f29246734561c90f36e70ed0506b61aa3d044e4cc4cba559065a2a741fae"},
+    {file = "Cython-3.0.8-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1ab75242869ff71e5665fe5c96f3378e79e792fa3c11762641b6c5afbbbbe026"},
+    {file = "Cython-3.0.8-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6717c06e9cfc6c1df18543cd31a21f5d8e378a40f70c851fa2d34f0597037abc"},
+    {file = "Cython-3.0.8-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:9d3f74388db378a3c6fd06e79a809ed98df3f56484d317b81ee762dbf3c263e0"},
+    {file = "Cython-3.0.8-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:ae7ac561fd8253a9ae96311e91d12af5f701383564edc11d6338a7b60b285a6f"},
+    {file = "Cython-3.0.8-cp37-cp37m-win32.whl", hash = "sha256:97b2a45845b993304f1799664fa88da676ee19442b15fdcaa31f9da7e1acc434"},
+    {file = "Cython-3.0.8-cp37-cp37m-win_amd64.whl", hash = "sha256:9e2be2b340fea46fb849d378f9b80d3c08ff2e81e2bfbcdb656e2e3cd8c6b2dc"},
+    {file = "Cython-3.0.8-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:2cde23c555470db3f149ede78b518e8274853745289c956a0e06ad8d982e4db9"},
+    {file = "Cython-3.0.8-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7990ca127e1f1beedaf8fc8bf66541d066ef4723ad7d8d47a7cbf842e0f47580"},
+    {file = "Cython-3.0.8-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4b983c8e6803f016146c26854d9150ddad5662960c804ea7f0c752c9266752f0"},
+    {file = "Cython-3.0.8-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a973268d7ca1a2bdf78575e459a94a78e1a0a9bb62a7db0c50041949a73b02ff"},
+    {file = "Cython-3.0.8-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:61a237bc9dd23c7faef0fcfce88c11c65d0c9bb73c74ccfa408b3a012073c20e"},
+    {file = "Cython-3.0.8-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:3a3d67f079598af49e90ff9655bf85bd358f093d727eb21ca2708f467c489cae"},
+    {file = "Cython-3.0.8-cp38-cp38-win32.whl", hash = "sha256:17a642bb01a693e34c914106566f59844b4461665066613913463a719e0dd15d"},
+    {file = "Cython-3.0.8-cp38-cp38-win_amd64.whl", hash = "sha256:2cdfc32252f3b6dc7c94032ab744dcedb45286733443c294d8f909a4854e7f83"},
+    {file = "Cython-3.0.8-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:fa97893d99385386925d00074654aeae3a98867f298d1e12ceaf38a9054a9bae"},
+    {file = "Cython-3.0.8-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f05c0bf9d085c031df8f583f0d506aa3be1692023de18c45d0aaf78685bbb944"},
+    {file = "Cython-3.0.8-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:de892422582f5758bd8de187e98ac829330ec1007bc42c661f687792999988a7"},
+    {file = "Cython-3.0.8-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:314f2355a1f1d06e3c431eaad4708cf10037b5e91e4b231d89c913989d0bdafd"},
+    {file = "Cython-3.0.8-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:78825a3774211e7d5089730f00cdf7f473042acc9ceb8b9eeebe13ed3a5541de"},
+    {file = "Cython-3.0.8-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:df8093deabc55f37028190cf5e575c26aad23fc673f34b85d5f45076bc37ce39"},
+    {file = "Cython-3.0.8-cp39-cp39-win32.whl", hash = "sha256:1aca1b97e0095b3a9a6c33eada3f661a4ed0d499067d121239b193e5ba3bb4f0"},
+    {file = "Cython-3.0.8-cp39-cp39-win_amd64.whl", hash = "sha256:16873d78be63bd38ffb759da7ab82814b36f56c769ee02b1d5859560e4c3ac3c"},
+    {file = "Cython-3.0.8-py2.py3-none-any.whl", hash = "sha256:171b27051253d3f9108e9759e504ba59ff06e7f7ba944457f94deaf9c21bf0b6"},
+    {file = "Cython-3.0.8.tar.gz", hash = "sha256:8333423d8fd5765e7cceea3a9985dd1e0a5dfeb2734629e1a2ed2d6233d39de6"},
+]
+
+[[package]]
+name = "decorator"
+version = "5.1.1"
+description = "Decorators for Humans"
+optional = false
+python-versions = ">=3.5"
+files = [
+    {file = "decorator-5.1.1-py3-none-any.whl", hash = "sha256:b8c3f85900b9dc423225913c5aace94729fe1fa9763b38939a95226f02d37186"},
+    {file = "decorator-5.1.1.tar.gz", hash = "sha256:637996211036b6385ef91435e4fae22989472f9d571faba8927ba8253acbc330"},
+]
+
+[[package]]
+name = "exceptiongroup"
+version = "1.2.0"
+description = "Backport of PEP 654 (exception groups)"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "exceptiongroup-1.2.0-py3-none-any.whl", hash = "sha256:4bfd3996ac73b41e9b9628b04e079f193850720ea5945fc96a08633c66912f14"},
+    {file = "exceptiongroup-1.2.0.tar.gz", hash = "sha256:91f5c769735f051a4290d52edd0858999b57e5876e9f85937691bd4c9fa3ed68"},
+]
+
+[package.extras]
+test = ["pytest (>=6)"]
+
+[[package]]
+name = "fairseq"
+version = "0.12.2"
+description = "Facebook AI Research Sequence-to-Sequence Toolkit"
+optional = false
+python-versions = "*"
+files = []
+develop = false
+
+[package.dependencies]
+bitarray = "*"
+cffi = "*"
+cython = "*"
+hydra-core = ">=1.3.2"
+numpy = ">=1.21.3"
+omegaconf = ">2.1"
+packaging = "*"
+regex = "*"
+sacrebleu = ">=1.4.12"
+scikit-learn = "*"
+torch = ">=1.13"
+torchaudio = ">=0.8.0"
+tqdm = "*"
+
+[package.extras]
+dev = ["black (==22.3.0)", "flake8", "pytest"]
+docs = ["sphinx", "sphinx-argparse"]
+
+[package.source]
+type = "git"
+url = "https://github.com/Tps-F/fairseq.git"
+reference = "main"
+resolved_reference = "ff08af27e302625a27d3502b0791a9367c8af0c7"
+
+[[package]]
+name = "faiss-cpu"
+version = "1.7.4"
+description = "A library for efficient similarity search and clustering of dense vectors."
+optional = false
+python-versions = "*"
+files = [
+    {file = "faiss-cpu-1.7.4.tar.gz", hash = "sha256:265dc31b0c079bf4433303bf6010f73922490adff9188b915e2d3f5e9c82dd0a"},
+    {file = "faiss_cpu-1.7.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:50d4ebe7f1869483751c558558504f818980292a9b55be36f9a1ee1009d9a686"},
+    {file = "faiss_cpu-1.7.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:7b1db7fae7bd8312aeedd0c41536bcd19a6e297229e1dce526bde3a73ab8c0b5"},
+    {file = "faiss_cpu-1.7.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:17b7fa7194a228a84929d9e6619d0e7dbf00cc0f717e3462253766f5e3d07de8"},
+    {file = "faiss_cpu-1.7.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dca531952a2e3eac56f479ff22951af4715ee44788a3fe991d208d766d3f95f3"},
+    {file = "faiss_cpu-1.7.4-cp310-cp310-win_amd64.whl", hash = "sha256:7173081d605e74766f950f2e3d6568a6f00c53f32fd9318063e96728c6c62821"},
+    {file = "faiss_cpu-1.7.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d0bbd6f55d7940cc0692f79e32a58c66106c3c950cee2341b05722de9da23ea3"},
+    {file = "faiss_cpu-1.7.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e13c14280376100f143767d0efe47dcb32618f69e62bbd3ea5cd38c2e1755926"},
+    {file = "faiss_cpu-1.7.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c521cb8462f3b00c0c7dfb11caff492bb67816528b947be28a3b76373952c41d"},
+    {file = "faiss_cpu-1.7.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:afdd9fe1141117fed85961fd36ee627c83fc3b9fd47bafb52d3c849cc2f088b7"},
+    {file = "faiss_cpu-1.7.4-cp311-cp311-win_amd64.whl", hash = "sha256:2ff7f57889ea31d945e3b87275be3cad5d55b6261a4e3f51c7aba304d76b81fb"},
+    {file = "faiss_cpu-1.7.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:eeaf92f27d76249fb53c1adafe617b0f217ab65837acf7b4ec818511caf6e3d8"},
+    {file = "faiss_cpu-1.7.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:102b1bd763e9b0c281ac312590af3eaf1c8b663ccbc1145821fe6a9f92b8eaaf"},
+    {file = "faiss_cpu-1.7.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5512da6707c967310c46ff712b00418b7ae28e93cb609726136e826e9f2f14fa"},
+    {file = "faiss_cpu-1.7.4-cp37-cp37m-win_amd64.whl", hash = "sha256:0c2e5b9d8c28c99f990e87379d5bbcc6c914da91ebb4250166864fd12db5755b"},
+    {file = "faiss_cpu-1.7.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:43f67f325393145d360171cd98786fcea6120ce50397319afd3bb78be409fb8a"},
+    {file = "faiss_cpu-1.7.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:6a4e4af194b8fce74c4b770cad67ad1dd1b4673677fc169723e4c50ba5bd97a8"},
+    {file = "faiss_cpu-1.7.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:31bfb7b9cffc36897ae02a983e04c09fe3b8c053110a287134751a115334a1df"},
+    {file = "faiss_cpu-1.7.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:52d7de96abef2340c0d373c1f5cbc78026a3cebb0f8f3a5920920a00210ead1f"},
+    {file = "faiss_cpu-1.7.4-cp38-cp38-win_amd64.whl", hash = "sha256:699feef85b23c2c729d794e26ca69bebc0bee920d676028c06fd0e0becc15c7e"},
+    {file = "faiss_cpu-1.7.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:559a0133f5ed44422acb09ee1ac0acffd90c6666d1bc0d671c18f6e93ad603e2"},
+    {file = "faiss_cpu-1.7.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:ea1d71539fe3dc0f1bed41ef954ca701678776f231046bf0ca22ccea5cf5bef6"},
+    {file = "faiss_cpu-1.7.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:12d45e0157024eb3249842163162983a1ac8b458f1a8b17bbf86f01be4585a99"},
+    {file = "faiss_cpu-1.7.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2f0eab359e066d32c874f51a7d4bf6440edeec068b7fe47e6d803c73605a8b4c"},
+    {file = "faiss_cpu-1.7.4-cp39-cp39-win_amd64.whl", hash = "sha256:98459ceeeb735b9df1a5b94572106ffe0a6ce740eb7e4626715dd218657bb4dc"},
+]
+
+[[package]]
+name = "fastapi"
+version = "0.109.0"
+description = "FastAPI framework, high performance, easy to learn, fast to code, ready for production"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "fastapi-0.109.0-py3-none-any.whl", hash = "sha256:8c77515984cd8e8cfeb58364f8cc7a28f0692088475e2614f7bf03275eba9093"},
+    {file = "fastapi-0.109.0.tar.gz", hash = "sha256:b978095b9ee01a5cf49b19f4bc1ac9b8ca83aa076e770ef8fd9af09a2b88d191"},
+]
+
+[package.dependencies]
+pydantic = ">=1.7.4,<1.8 || >1.8,<1.8.1 || >1.8.1,<2.0.0 || >2.0.0,<2.0.1 || >2.0.1,<2.1.0 || >2.1.0,<3.0.0"
+starlette = ">=0.35.0,<0.36.0"
+typing-extensions = ">=4.8.0"
+
+[package.extras]
+all = ["email-validator (>=2.0.0)", "httpx (>=0.23.0)", "itsdangerous (>=1.1.0)", "jinja2 (>=2.11.2)", "orjson (>=3.2.1)", "pydantic-extra-types (>=2.0.0)", "pydantic-settings (>=2.0.0)", "python-multipart (>=0.0.5)", "pyyaml (>=5.3.1)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0)", "uvicorn[standard] (>=0.12.0)"]
+
+[[package]]
+name = "filelock"
+version = "3.13.1"
+description = "A platform independent file lock."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "filelock-3.13.1-py3-none-any.whl", hash = "sha256:57dbda9b35157b05fb3e58ee91448612eb674172fab98ee235ccb0b5bee19a1c"},
+    {file = "filelock-3.13.1.tar.gz", hash = "sha256:521f5f56c50f8426f5e03ad3b281b490a87ef15bc6c526f168290f0c7148d44e"},
+]
+
+[package.extras]
+docs = ["furo (>=2023.9.10)", "sphinx (>=7.2.6)", "sphinx-autodoc-typehints (>=1.24)"]
+testing = ["covdefaults (>=2.3)", "coverage (>=7.3.2)", "diff-cover (>=8)", "pytest (>=7.4.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)", "pytest-timeout (>=2.2)"]
+typing = ["typing-extensions (>=4.8)"]
+
+[[package]]
+name = "fsspec"
+version = "2023.12.2"
+description = "File-system specification"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "fsspec-2023.12.2-py3-none-any.whl", hash = "sha256:d800d87f72189a745fa3d6b033b9dc4a34ad069f60ca60b943a63599f5501960"},
+    {file = "fsspec-2023.12.2.tar.gz", hash = "sha256:8548d39e8810b59c38014934f6b31e57f40c1b20f911f4cc2b85389c7e9bf0cb"},
+]
+
+[package.extras]
+abfs = ["adlfs"]
+adl = ["adlfs"]
+arrow = ["pyarrow (>=1)"]
+dask = ["dask", "distributed"]
+devel = ["pytest", "pytest-cov"]
+dropbox = ["dropbox", "dropboxdrivefs", "requests"]
+full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "dask", "distributed", "dropbox", "dropboxdrivefs", "fusepy", "gcsfs", "libarchive-c", "ocifs", "panel", "paramiko", "pyarrow (>=1)", "pygit2", "requests", "s3fs", "smbprotocol", "tqdm"]
+fuse = ["fusepy"]
+gcs = ["gcsfs"]
+git = ["pygit2"]
+github = ["requests"]
+gs = ["gcsfs"]
+gui = ["panel"]
+hdfs = ["pyarrow (>=1)"]
+http = ["aiohttp (!=4.0.0a0,!=4.0.0a1)", "requests"]
+libarchive = ["libarchive-c"]
+oci = ["ocifs"]
+s3 = ["s3fs"]
+sftp = ["paramiko"]
+smb = ["smbprotocol"]
+ssh = ["paramiko"]
+tqdm = ["tqdm"]
+
+[[package]]
+name = "h11"
+version = "0.14.0"
+description = "A pure-Python, bring-your-own-I/O implementation of HTTP/1.1"
+optional = true
+python-versions = ">=3.7"
+files = [
+    {file = "h11-0.14.0-py3-none-any.whl", hash = "sha256:e3fe4ac4b851c468cc8363d500db52c2ead036020723024a109d37346efaa761"},
+    {file = "h11-0.14.0.tar.gz", hash = "sha256:8f19fbbe99e72420ff35c00b27a34cb9937e902a8b810e2c88300c6f0a3b699d"},
+]
+
+[[package]]
+name = "hydra-core"
+version = "1.3.2"
+description = "A framework for elegantly configuring complex applications"
+optional = false
+python-versions = "*"
+files = [
+    {file = "hydra-core-1.3.2.tar.gz", hash = "sha256:8a878ed67216997c3e9d88a8e72e7b4767e81af37afb4ea3334b269a4390a824"},
+    {file = "hydra_core-1.3.2-py3-none-any.whl", hash = "sha256:fa0238a9e31df3373b35b0bfb672c34cc92718d21f81311d8996a16de1141d8b"},
+]
+
+[package.dependencies]
+antlr4-python3-runtime = "==4.9.*"
+omegaconf = ">=2.2,<2.4"
+packaging = "*"
+
+[[package]]
+name = "idna"
+version = "3.6"
+description = "Internationalized Domain Names in Applications (IDNA)"
+optional = false
+python-versions = ">=3.5"
+files = [
+    {file = "idna-3.6-py3-none-any.whl", hash = "sha256:c05567e9c24a6b9faaa835c4821bad0590fbb9d5779e7caa6e1cc4978e7eb24f"},
+    {file = "idna-3.6.tar.gz", hash = "sha256:9ecdbbd083b06798ae1e86adcbfe8ab1479cf864e4ee30fe4e46a003d12491ca"},
+]
+
+[[package]]
+name = "jinja2"
+version = "3.1.3"
+description = "A very fast and expressive template engine."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "Jinja2-3.1.3-py3-none-any.whl", hash = "sha256:7d6d50dd97d52cbc355597bd845fabfbac3f551e1f99619e39a35ce8c370b5fa"},
+    {file = "Jinja2-3.1.3.tar.gz", hash = "sha256:ac8bd6544d4bb2c9792bf3a159e80bba8fda7f07e81bc3aed565432d5925ba90"},
+]
+
+[package.dependencies]
+MarkupSafe = ">=2.0"
+
+[package.extras]
+i18n = ["Babel (>=2.7)"]
+
+[[package]]
+name = "joblib"
+version = "1.3.2"
+description = "Lightweight pipelining with Python functions"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "joblib-1.3.2-py3-none-any.whl", hash = "sha256:ef4331c65f239985f3f2220ecc87db222f08fd22097a3dd5698f693875f8cbb9"},
+    {file = "joblib-1.3.2.tar.gz", hash = "sha256:92f865e621e17784e7955080b6d042489e3b8e294949cc44c6eac304f59772b1"},
+]
+
+[[package]]
+name = "lazy-loader"
+version = "0.3"
+description = "lazy_loader"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "lazy_loader-0.3-py3-none-any.whl", hash = "sha256:1e9e76ee8631e264c62ce10006718e80b2cfc74340d17d1031e0f84af7478554"},
+    {file = "lazy_loader-0.3.tar.gz", hash = "sha256:3b68898e34f5b2a29daaaac172c6555512d0f32074f147e2254e4a6d9d838f37"},
+]
+
+[package.extras]
+lint = ["pre-commit (>=3.3)"]
+test = ["pytest (>=7.4)", "pytest-cov (>=4.1)"]
+
+[[package]]
+name = "librosa"
+version = "0.10.1"
+description = "Python module for audio and music processing"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "librosa-0.10.1-py3-none-any.whl", hash = "sha256:7ab91d9f5fcb75ea14848a05d3b1f825cf8d0c42ca160d19ae6874f2de2d8223"},
+    {file = "librosa-0.10.1.tar.gz", hash = "sha256:832f7d150d6dd08ed2aa08c0567a4be58330635c32ddd2208de9bc91300802c7"},
+]
+
+[package.dependencies]
+audioread = ">=2.1.9"
+decorator = ">=4.3.0"
+joblib = ">=0.14"
+lazy-loader = ">=0.1"
+msgpack = ">=1.0"
+numba = ">=0.51.0"
+numpy = ">=1.20.3,<1.22.0 || >1.22.0,<1.22.1 || >1.22.1,<1.22.2 || >1.22.2"
+pooch = ">=1.0"
+scikit-learn = ">=0.20.0"
+scipy = ">=1.2.0"
+soundfile = ">=0.12.1"
+soxr = ">=0.3.2"
+typing-extensions = ">=4.1.1"
+
+[package.extras]
+display = ["matplotlib (>=3.3.0)"]
+docs = ["ipython (>=7.0)", "matplotlib (>=3.3.0)", "mir-eval (>=0.5)", "numba (>=0.51)", "numpydoc", "presets", "sphinx (!=1.3.1)", "sphinx-gallery (>=0.7)", "sphinx-multiversion (>=0.2.3)", "sphinx-rtd-theme (>=1.2.0)", "sphinxcontrib-svg2pdfconverter"]
+tests = ["matplotlib (>=3.3.0)", "packaging (>=20.0)", "pytest", "pytest-cov", "pytest-mpl", "resampy (>=0.2.2)", "samplerate", "types-decorator"]
+
+[[package]]
+name = "llvmlite"
+version = "0.42.0rc1"
+description = "lightweight wrapper around basic LLVM functionality"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "llvmlite-0.42.0rc1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:59ca5d262d23a0aee7ede2eb7fed7f3df6d6b78de79136fe9898ea888ec89e05"},
+    {file = "llvmlite-0.42.0rc1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e643e7817cd8c99b9d2d2dfdfa9c147127bc011787cda6f6c462e38af142c8be"},
+    {file = "llvmlite-0.42.0rc1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c69a2d9f8020f19c5f0455685a83990777c117208275195763f3a9533ac24233"},
+    {file = "llvmlite-0.42.0rc1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:93bd9d9e81ab3d8096eac3ced83b75eaca39fe9ef51fa1a51a993e9408030f33"},
+    {file = "llvmlite-0.42.0rc1-cp310-cp310-win_amd64.whl", hash = "sha256:959f005565092ef4dd6f5bc5fe32ce1aaf97a02b45f34e39df6e2d200779935f"},
+    {file = "llvmlite-0.42.0rc1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c318e8145bef02a8ddc34418041f655b3b49fbaf66b996b4a1afca66fe58941b"},
+    {file = "llvmlite-0.42.0rc1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:6ef844e95c5b57d5c569ec5cfc7b440924878134f1a801b3f43e79a91a13cef0"},
+    {file = "llvmlite-0.42.0rc1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8c10c55be06f2cd7f36c5e69aef05cc4463bc30d998eea49ef39579370301244"},
+    {file = "llvmlite-0.42.0rc1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a52b4b53842a39e118c1ff536350da9b3869f2dff076cfae1bb76ab702c59188"},
+    {file = "llvmlite-0.42.0rc1-cp311-cp311-win_amd64.whl", hash = "sha256:399e98514c54860c46ff722f08b9b0803aa68540d94149f1ac7efe5429068691"},
+    {file = "llvmlite-0.42.0rc1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:9920c847d828593626023a5789ad269751667ab006be6e6643a084db35b332a2"},
+    {file = "llvmlite-0.42.0rc1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:cfa847d8f0ef9665e3e20270b3ef136cdbcef49d085208ff303a98c2674aef62"},
+    {file = "llvmlite-0.42.0rc1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2fbed1ef1463a7339d917efd144045b6b8e05af840a970d375c8ec42ae383e8d"},
+    {file = "llvmlite-0.42.0rc1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f59485b2d9db140350366e1566fbfbd378ce34e0c013cb72d432bb8af1a6c889"},
+    {file = "llvmlite-0.42.0rc1-cp312-cp312-win_amd64.whl", hash = "sha256:df4068e11ff9c46072df7ace550765efe25deaad8fa75e7429cea57ad8b2d815"},
+    {file = "llvmlite-0.42.0rc1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:b3ade537d62a30cda772327fc34f902af42b138e8c9d73b2960c2d4046dfdc39"},
+    {file = "llvmlite-0.42.0rc1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:971ff50e4e7f287b796fa527106648808cfd7e4ea34a391b379beb0c58a46b4a"},
+    {file = "llvmlite-0.42.0rc1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fd46f7b03f172131ee8d33e15da23ca2cfa7c53c9cdef777bf86f4cbba33e20b"},
+    {file = "llvmlite-0.42.0rc1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f8a6584bf556542f6aeb6ee91adb00cbaf78d50f07e0be63e6e5aff21f7cdffd"},
+    {file = "llvmlite-0.42.0rc1-cp39-cp39-win_amd64.whl", hash = "sha256:ebb5db67cbc1437dafea2bdb585516d5bb2a52af1b00f0d0ea0890c80503bbf8"},
+    {file = "llvmlite-0.42.0rc1.tar.gz", hash = "sha256:01a057fc242bbd875cb44b373538c50172e09bf6cf559da12eb48197a7f4b116"},
+]
+
+[[package]]
+name = "lxml"
+version = "5.1.0"
+description = "Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API."
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "lxml-5.1.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:704f5572ff473a5f897745abebc6df40f22d4133c1e0a1f124e4f2bd3330ff7e"},
+    {file = "lxml-5.1.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:9d3c0f8567ffe7502d969c2c1b809892dc793b5d0665f602aad19895f8d508da"},
+    {file = "lxml-5.1.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:5fcfbebdb0c5d8d18b84118842f31965d59ee3e66996ac842e21f957eb76138c"},
+    {file = "lxml-5.1.0-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2f37c6d7106a9d6f0708d4e164b707037b7380fcd0b04c5bd9cae1fb46a856fb"},
+    {file = "lxml-5.1.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2befa20a13f1a75c751f47e00929fb3433d67eb9923c2c0b364de449121f447c"},
+    {file = "lxml-5.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:22b7ee4c35f374e2c20337a95502057964d7e35b996b1c667b5c65c567d2252a"},
+    {file = "lxml-5.1.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:bf8443781533b8d37b295016a4b53c1494fa9a03573c09ca5104550c138d5c05"},
+    {file = "lxml-5.1.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:82bddf0e72cb2af3cbba7cec1d2fd11fda0de6be8f4492223d4a268713ef2147"},
+    {file = "lxml-5.1.0-cp310-cp310-win32.whl", hash = "sha256:b66aa6357b265670bb574f050ffceefb98549c721cf28351b748be1ef9577d93"},
+    {file = "lxml-5.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:4946e7f59b7b6a9e27bef34422f645e9a368cb2be11bf1ef3cafc39a1f6ba68d"},
+    {file = "lxml-5.1.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:14deca1460b4b0f6b01f1ddc9557704e8b365f55c63070463f6c18619ebf964f"},
+    {file = "lxml-5.1.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:ed8c3d2cd329bf779b7ed38db176738f3f8be637bb395ce9629fc76f78afe3d4"},
+    {file = "lxml-5.1.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:436a943c2900bb98123b06437cdd30580a61340fbdb7b28aaf345a459c19046a"},
+    {file = "lxml-5.1.0-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:acb6b2f96f60f70e7f34efe0c3ea34ca63f19ca63ce90019c6cbca6b676e81fa"},
+    {file = "lxml-5.1.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:af8920ce4a55ff41167ddbc20077f5698c2e710ad3353d32a07d3264f3a2021e"},
+    {file = "lxml-5.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7cfced4a069003d8913408e10ca8ed092c49a7f6cefee9bb74b6b3e860683b45"},
+    {file = "lxml-5.1.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:9e5ac3437746189a9b4121db2a7b86056ac8786b12e88838696899328fc44bb2"},
+    {file = "lxml-5.1.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:f4c9bda132ad108b387c33fabfea47866af87f4ea6ffb79418004f0521e63204"},
+    {file = "lxml-5.1.0-cp311-cp311-win32.whl", hash = "sha256:bc64d1b1dab08f679fb89c368f4c05693f58a9faf744c4d390d7ed1d8223869b"},
+    {file = "lxml-5.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:a5ab722ae5a873d8dcee1f5f45ddd93c34210aed44ff2dc643b5025981908cda"},
+    {file = "lxml-5.1.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:9aa543980ab1fbf1720969af1d99095a548ea42e00361e727c58a40832439114"},
+    {file = "lxml-5.1.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:6f11b77ec0979f7e4dc5ae081325a2946f1fe424148d3945f943ceaede98adb8"},
+    {file = "lxml-5.1.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a36c506e5f8aeb40680491d39ed94670487ce6614b9d27cabe45d94cd5d63e1e"},
+    {file = "lxml-5.1.0-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f643ffd2669ffd4b5a3e9b41c909b72b2a1d5e4915da90a77e119b8d48ce867a"},
+    {file = "lxml-5.1.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:16dd953fb719f0ffc5bc067428fc9e88f599e15723a85618c45847c96f11f431"},
+    {file = "lxml-5.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:16018f7099245157564d7148165132c70adb272fb5a17c048ba70d9cc542a1a1"},
+    {file = "lxml-5.1.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:82cd34f1081ae4ea2ede3d52f71b7be313756e99b4b5f829f89b12da552d3aa3"},
+    {file = "lxml-5.1.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:19a1bc898ae9f06bccb7c3e1dfd73897ecbbd2c96afe9095a6026016e5ca97b8"},
+    {file = "lxml-5.1.0-cp312-cp312-win32.whl", hash = "sha256:13521a321a25c641b9ea127ef478b580b5ec82aa2e9fc076c86169d161798b01"},
+    {file = "lxml-5.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:1ad17c20e3666c035db502c78b86e58ff6b5991906e55bdbef94977700c72623"},
+    {file = "lxml-5.1.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:24ef5a4631c0b6cceaf2dbca21687e29725b7c4e171f33a8f8ce23c12558ded1"},
+    {file = "lxml-5.1.0-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8d2900b7f5318bc7ad8631d3d40190b95ef2aa8cc59473b73b294e4a55e9f30f"},
+    {file = "lxml-5.1.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:601f4a75797d7a770daed8b42b97cd1bb1ba18bd51a9382077a6a247a12aa38d"},
+    {file = "lxml-5.1.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b4b68c961b5cc402cbd99cca5eb2547e46ce77260eb705f4d117fd9c3f932b95"},
+    {file = "lxml-5.1.0-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:afd825e30f8d1f521713a5669b63657bcfe5980a916c95855060048b88e1adb7"},
+    {file = "lxml-5.1.0-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:262bc5f512a66b527d026518507e78c2f9c2bd9eb5c8aeeb9f0eb43fcb69dc67"},
+    {file = "lxml-5.1.0-cp36-cp36m-win32.whl", hash = "sha256:e856c1c7255c739434489ec9c8aa9cdf5179785d10ff20add308b5d673bed5cd"},
+    {file = "lxml-5.1.0-cp36-cp36m-win_amd64.whl", hash = "sha256:c7257171bb8d4432fe9d6fdde4d55fdbe663a63636a17f7f9aaba9bcb3153ad7"},
+    {file = "lxml-5.1.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:b9e240ae0ba96477682aa87899d94ddec1cc7926f9df29b1dd57b39e797d5ab5"},
+    {file = "lxml-5.1.0-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a96f02ba1bcd330807fc060ed91d1f7a20853da6dd449e5da4b09bfcc08fdcf5"},
+    {file = "lxml-5.1.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3e3898ae2b58eeafedfe99e542a17859017d72d7f6a63de0f04f99c2cb125936"},
+    {file = "lxml-5.1.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:61c5a7edbd7c695e54fca029ceb351fc45cd8860119a0f83e48be44e1c464862"},
+    {file = "lxml-5.1.0-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:3aeca824b38ca78d9ee2ab82bd9883083d0492d9d17df065ba3b94e88e4d7ee6"},
+    {file = "lxml-5.1.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:8f52fe6859b9db71ee609b0c0a70fea5f1e71c3462ecf144ca800d3f434f0764"},
+    {file = "lxml-5.1.0-cp37-cp37m-win32.whl", hash = "sha256:d42e3a3fc18acc88b838efded0e6ec3edf3e328a58c68fbd36a7263a874906c8"},
+    {file = "lxml-5.1.0-cp37-cp37m-win_amd64.whl", hash = "sha256:eac68f96539b32fce2c9b47eb7c25bb2582bdaf1bbb360d25f564ee9e04c542b"},
+    {file = "lxml-5.1.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:ae15347a88cf8af0949a9872b57a320d2605ae069bcdf047677318bc0bba45b1"},
+    {file = "lxml-5.1.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:c26aab6ea9c54d3bed716b8851c8bfc40cb249b8e9880e250d1eddde9f709bf5"},
+    {file = "lxml-5.1.0-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:342e95bddec3a698ac24378d61996b3ee5ba9acfeb253986002ac53c9a5f6f84"},
+    {file = "lxml-5.1.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:725e171e0b99a66ec8605ac77fa12239dbe061482ac854d25720e2294652eeaa"},
+    {file = "lxml-5.1.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3d184e0d5c918cff04cdde9dbdf9600e960161d773666958c9d7b565ccc60c45"},
+    {file = "lxml-5.1.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:98f3f020a2b736566c707c8e034945c02aa94e124c24f77ca097c446f81b01f1"},
+    {file = "lxml-5.1.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:6d48fc57e7c1e3df57be5ae8614bab6d4e7b60f65c5457915c26892c41afc59e"},
+    {file = "lxml-5.1.0-cp38-cp38-win32.whl", hash = "sha256:7ec465e6549ed97e9f1e5ed51c657c9ede767bc1c11552f7f4d022c4df4a977a"},
+    {file = "lxml-5.1.0-cp38-cp38-win_amd64.whl", hash = "sha256:b21b4031b53d25b0858d4e124f2f9131ffc1530431c6d1321805c90da78388d1"},
+    {file = "lxml-5.1.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:52427a7eadc98f9e62cb1368a5079ae826f94f05755d2d567d93ee1bc3ceb354"},
+    {file = "lxml-5.1.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:6a2a2c724d97c1eb8cf966b16ca2915566a4904b9aad2ed9a09c748ffe14f969"},
+    {file = "lxml-5.1.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:843b9c835580d52828d8f69ea4302537337a21e6b4f1ec711a52241ba4a824f3"},
+    {file = "lxml-5.1.0-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9b99f564659cfa704a2dd82d0684207b1aadf7d02d33e54845f9fc78e06b7581"},
+    {file = "lxml-5.1.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4f8b0c78e7aac24979ef09b7f50da871c2de2def043d468c4b41f512d831e912"},
+    {file = "lxml-5.1.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9bcf86dfc8ff3e992fed847c077bd875d9e0ba2fa25d859c3a0f0f76f07f0c8d"},
+    {file = "lxml-5.1.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:49a9b4af45e8b925e1cd6f3b15bbba2c81e7dba6dce170c677c9cda547411e14"},
+    {file = "lxml-5.1.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:280f3edf15c2a967d923bcfb1f8f15337ad36f93525828b40a0f9d6c2ad24890"},
+    {file = "lxml-5.1.0-cp39-cp39-win32.whl", hash = "sha256:ed7326563024b6e91fef6b6c7a1a2ff0a71b97793ac33dbbcf38f6005e51ff6e"},
+    {file = "lxml-5.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:8d7b4beebb178e9183138f552238f7e6613162a42164233e2bda00cb3afac58f"},
+    {file = "lxml-5.1.0-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:9bd0ae7cc2b85320abd5e0abad5ccee5564ed5f0cc90245d2f9a8ef330a8deae"},
+    {file = "lxml-5.1.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d8c1d679df4361408b628f42b26a5d62bd3e9ba7f0c0e7969f925021554755aa"},
+    {file = "lxml-5.1.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:2ad3a8ce9e8a767131061a22cd28fdffa3cd2dc193f399ff7b81777f3520e372"},
+    {file = "lxml-5.1.0-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:304128394c9c22b6569eba2a6d98392b56fbdfbad58f83ea702530be80d0f9df"},
+    {file = "lxml-5.1.0-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d74fcaf87132ffc0447b3c685a9f862ffb5b43e70ea6beec2fb8057d5d2a1fea"},
+    {file = "lxml-5.1.0-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:8cf5877f7ed384dabfdcc37922c3191bf27e55b498fecece9fd5c2c7aaa34c33"},
+    {file = "lxml-5.1.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:877efb968c3d7eb2dad540b6cabf2f1d3c0fbf4b2d309a3c141f79c7e0061324"},
+    {file = "lxml-5.1.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3f14a4fb1c1c402a22e6a341a24c1341b4a3def81b41cd354386dcb795f83897"},
+    {file = "lxml-5.1.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:25663d6e99659544ee8fe1b89b1a8c0aaa5e34b103fab124b17fa958c4a324a6"},
+    {file = "lxml-5.1.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:8b9f19df998761babaa7f09e6bc169294eefafd6149aaa272081cbddc7ba4ca3"},
+    {file = "lxml-5.1.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5e53d7e6a98b64fe54775d23a7c669763451340c3d44ad5e3a3b48a1efbdc96f"},
+    {file = "lxml-5.1.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:c3cd1fc1dc7c376c54440aeaaa0dcc803d2126732ff5c6b68ccd619f2e64be4f"},
+    {file = "lxml-5.1.0.tar.gz", hash = "sha256:3eea6ed6e6c918e468e693c41ef07f3c3acc310b70ddd9cc72d9ef84bc9564ca"},
+]
+
+[package.extras]
+cssselect = ["cssselect (>=0.7)"]
+html5 = ["html5lib"]
+htmlsoup = ["BeautifulSoup4"]
+source = ["Cython (>=3.0.7)"]
+
+[[package]]
+name = "markupsafe"
+version = "2.1.4"
+description = "Safely add untrusted strings to HTML/XML markup."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "MarkupSafe-2.1.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:de8153a7aae3835484ac168a9a9bdaa0c5eee4e0bc595503c95d53b942879c84"},
+    {file = "MarkupSafe-2.1.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:e888ff76ceb39601c59e219f281466c6d7e66bd375b4ec1ce83bcdc68306796b"},
+    {file = "MarkupSafe-2.1.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0b838c37ba596fcbfca71651a104a611543077156cb0a26fe0c475e1f152ee8"},
+    {file = "MarkupSafe-2.1.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dac1ebf6983148b45b5fa48593950f90ed6d1d26300604f321c74a9ca1609f8e"},
+    {file = "MarkupSafe-2.1.4-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0fbad3d346df8f9d72622ac71b69565e621ada2ce6572f37c2eae8dacd60385d"},
+    {file = "MarkupSafe-2.1.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:d5291d98cd3ad9a562883468c690a2a238c4a6388ab3bd155b0c75dd55ece858"},
+    {file = "MarkupSafe-2.1.4-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:a7cc49ef48a3c7a0005a949f3c04f8baa5409d3f663a1b36f0eba9bfe2a0396e"},
+    {file = "MarkupSafe-2.1.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b83041cda633871572f0d3c41dddd5582ad7d22f65a72eacd8d3d6d00291df26"},
+    {file = "MarkupSafe-2.1.4-cp310-cp310-win32.whl", hash = "sha256:0c26f67b3fe27302d3a412b85ef696792c4a2386293c53ba683a89562f9399b0"},
+    {file = "MarkupSafe-2.1.4-cp310-cp310-win_amd64.whl", hash = "sha256:a76055d5cb1c23485d7ddae533229039b850db711c554a12ea64a0fd8a0129e2"},
+    {file = "MarkupSafe-2.1.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:9e9e3c4020aa2dc62d5dd6743a69e399ce3de58320522948af6140ac959ab863"},
+    {file = "MarkupSafe-2.1.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:0042d6a9880b38e1dd9ff83146cc3c9c18a059b9360ceae207805567aacccc69"},
+    {file = "MarkupSafe-2.1.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:55d03fea4c4e9fd0ad75dc2e7e2b6757b80c152c032ea1d1de487461d8140efc"},
+    {file = "MarkupSafe-2.1.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ab3a886a237f6e9c9f4f7d272067e712cdb4efa774bef494dccad08f39d8ae6"},
+    {file = "MarkupSafe-2.1.4-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:abf5ebbec056817057bfafc0445916bb688a255a5146f900445d081db08cbabb"},
+    {file = "MarkupSafe-2.1.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:e1a0d1924a5013d4f294087e00024ad25668234569289650929ab871231668e7"},
+    {file = "MarkupSafe-2.1.4-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:e7902211afd0af05fbadcc9a312e4cf10f27b779cf1323e78d52377ae4b72bea"},
+    {file = "MarkupSafe-2.1.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:c669391319973e49a7c6230c218a1e3044710bc1ce4c8e6eb71f7e6d43a2c131"},
+    {file = "MarkupSafe-2.1.4-cp311-cp311-win32.whl", hash = "sha256:31f57d64c336b8ccb1966d156932f3daa4fee74176b0fdc48ef580be774aae74"},
+    {file = "MarkupSafe-2.1.4-cp311-cp311-win_amd64.whl", hash = "sha256:54a7e1380dfece8847c71bf7e33da5d084e9b889c75eca19100ef98027bd9f56"},
+    {file = "MarkupSafe-2.1.4-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:a76cd37d229fc385738bd1ce4cba2a121cf26b53864c1772694ad0ad348e509e"},
+    {file = "MarkupSafe-2.1.4-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:987d13fe1d23e12a66ca2073b8d2e2a75cec2ecb8eab43ff5624ba0ad42764bc"},
+    {file = "MarkupSafe-2.1.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5244324676254697fe5c181fc762284e2c5fceeb1c4e3e7f6aca2b6f107e60dc"},
+    {file = "MarkupSafe-2.1.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:78bc995e004681246e85e28e068111a4c3f35f34e6c62da1471e844ee1446250"},
+    {file = "MarkupSafe-2.1.4-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a4d176cfdfde84f732c4a53109b293d05883e952bbba68b857ae446fa3119b4f"},
+    {file = "MarkupSafe-2.1.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:f9917691f410a2e0897d1ef99619fd3f7dd503647c8ff2475bf90c3cf222ad74"},
+    {file = "MarkupSafe-2.1.4-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:f06e5a9e99b7df44640767842f414ed5d7bedaaa78cd817ce04bbd6fd86e2dd6"},
+    {file = "MarkupSafe-2.1.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:396549cea79e8ca4ba65525470d534e8a41070e6b3500ce2414921099cb73e8d"},
+    {file = "MarkupSafe-2.1.4-cp312-cp312-win32.whl", hash = "sha256:f6be2d708a9d0e9b0054856f07ac7070fbe1754be40ca8525d5adccdbda8f475"},
+    {file = "MarkupSafe-2.1.4-cp312-cp312-win_amd64.whl", hash = "sha256:5045e892cfdaecc5b4c01822f353cf2c8feb88a6ec1c0adef2a2e705eef0f656"},
+    {file = "MarkupSafe-2.1.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:7a07f40ef8f0fbc5ef1000d0c78771f4d5ca03b4953fc162749772916b298fc4"},
+    {file = "MarkupSafe-2.1.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d18b66fe626ac412d96c2ab536306c736c66cf2a31c243a45025156cc190dc8a"},
+    {file = "MarkupSafe-2.1.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:698e84142f3f884114ea8cf83e7a67ca8f4ace8454e78fe960646c6c91c63bfa"},
+    {file = "MarkupSafe-2.1.4-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:49a3b78a5af63ec10d8604180380c13dcd870aba7928c1fe04e881d5c792dc4e"},
+    {file = "MarkupSafe-2.1.4-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:15866d7f2dc60cfdde12ebb4e75e41be862348b4728300c36cdf405e258415ec"},
+    {file = "MarkupSafe-2.1.4-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:6aa5e2e7fc9bc042ae82d8b79d795b9a62bd8f15ba1e7594e3db243f158b5565"},
+    {file = "MarkupSafe-2.1.4-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:54635102ba3cf5da26eb6f96c4b8c53af8a9c0d97b64bdcb592596a6255d8518"},
+    {file = "MarkupSafe-2.1.4-cp37-cp37m-win32.whl", hash = "sha256:3583a3a3ab7958e354dc1d25be74aee6228938312ee875a22330c4dc2e41beb0"},
+    {file = "MarkupSafe-2.1.4-cp37-cp37m-win_amd64.whl", hash = "sha256:d6e427c7378c7f1b2bef6a344c925b8b63623d3321c09a237b7cc0e77dd98ceb"},
+    {file = "MarkupSafe-2.1.4-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:bf1196dcc239e608605b716e7b166eb5faf4bc192f8a44b81e85251e62584bd2"},
+    {file = "MarkupSafe-2.1.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:4df98d4a9cd6a88d6a585852f56f2155c9cdb6aec78361a19f938810aa020954"},
+    {file = "MarkupSafe-2.1.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b835aba863195269ea358cecc21b400276747cc977492319fd7682b8cd2c253d"},
+    {file = "MarkupSafe-2.1.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:23984d1bdae01bee794267424af55eef4dfc038dc5d1272860669b2aa025c9e3"},
+    {file = "MarkupSafe-2.1.4-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1c98c33ffe20e9a489145d97070a435ea0679fddaabcafe19982fe9c971987d5"},
+    {file = "MarkupSafe-2.1.4-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:9896fca4a8eb246defc8b2a7ac77ef7553b638e04fbf170bff78a40fa8a91474"},
+    {file = "MarkupSafe-2.1.4-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:b0fe73bac2fed83839dbdbe6da84ae2a31c11cfc1c777a40dbd8ac8a6ed1560f"},
+    {file = "MarkupSafe-2.1.4-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:c7556bafeaa0a50e2fe7dc86e0382dea349ebcad8f010d5a7dc6ba568eaaa789"},
+    {file = "MarkupSafe-2.1.4-cp38-cp38-win32.whl", hash = "sha256:fc1a75aa8f11b87910ffd98de62b29d6520b6d6e8a3de69a70ca34dea85d2a8a"},
+    {file = "MarkupSafe-2.1.4-cp38-cp38-win_amd64.whl", hash = "sha256:3a66c36a3864df95e4f62f9167c734b3b1192cb0851b43d7cc08040c074c6279"},
+    {file = "MarkupSafe-2.1.4-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:765f036a3d00395a326df2835d8f86b637dbaf9832f90f5d196c3b8a7a5080cb"},
+    {file = "MarkupSafe-2.1.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:21e7af8091007bf4bebf4521184f4880a6acab8df0df52ef9e513d8e5db23411"},
+    {file = "MarkupSafe-2.1.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d5c31fe855c77cad679b302aabc42d724ed87c043b1432d457f4976add1c2c3e"},
+    {file = "MarkupSafe-2.1.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7653fa39578957bc42e5ebc15cf4361d9e0ee4b702d7d5ec96cdac860953c5b4"},
+    {file = "MarkupSafe-2.1.4-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:47bb5f0142b8b64ed1399b6b60f700a580335c8e1c57f2f15587bd072012decc"},
+    {file = "MarkupSafe-2.1.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:fe8512ed897d5daf089e5bd010c3dc03bb1bdae00b35588c49b98268d4a01e00"},
+    {file = "MarkupSafe-2.1.4-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:36d7626a8cca4d34216875aee5a1d3d654bb3dac201c1c003d182283e3205949"},
+    {file = "MarkupSafe-2.1.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:b6f14a9cd50c3cb100eb94b3273131c80d102e19bb20253ac7bd7336118a673a"},
+    {file = "MarkupSafe-2.1.4-cp39-cp39-win32.whl", hash = "sha256:c8f253a84dbd2c63c19590fa86a032ef3d8cc18923b8049d91bcdeeb2581fbf6"},
+    {file = "MarkupSafe-2.1.4-cp39-cp39-win_amd64.whl", hash = "sha256:8b570a1537367b52396e53325769608f2a687ec9a4363647af1cded8928af959"},
+    {file = "MarkupSafe-2.1.4.tar.gz", hash = "sha256:3aae9af4cac263007fd6309c64c6ab4506dd2b79382d9d19a1994f9240b8db4f"},
+]
+
+[[package]]
+name = "mpmath"
+version = "1.3.0"
+description = "Python library for arbitrary-precision floating-point arithmetic"
+optional = false
+python-versions = "*"
+files = [
+    {file = "mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c"},
+    {file = "mpmath-1.3.0.tar.gz", hash = "sha256:7a28eb2a9774d00c7bc92411c19a89209d5da7c4c9a9e227be8330a23a25b91f"},
+]
+
+[package.extras]
+develop = ["codecov", "pycodestyle", "pytest (>=4.6)", "pytest-cov", "wheel"]
+docs = ["sphinx"]
+gmpy = ["gmpy2 (>=2.1.0a4)"]
+tests = ["pytest (>=4.6)"]
+
+[[package]]
+name = "msgpack"
+version = "1.0.7"
+description = "MessagePack serializer"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "msgpack-1.0.7-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:04ad6069c86e531682f9e1e71b71c1c3937d6014a7c3e9edd2aa81ad58842862"},
+    {file = "msgpack-1.0.7-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:cca1b62fe70d761a282496b96a5e51c44c213e410a964bdffe0928e611368329"},
+    {file = "msgpack-1.0.7-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e50ebce52f41370707f1e21a59514e3375e3edd6e1832f5e5235237db933c98b"},
+    {file = "msgpack-1.0.7-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4a7b4f35de6a304b5533c238bee86b670b75b03d31b7797929caa7a624b5dda6"},
+    {file = "msgpack-1.0.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:28efb066cde83c479dfe5a48141a53bc7e5f13f785b92ddde336c716663039ee"},
+    {file = "msgpack-1.0.7-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4cb14ce54d9b857be9591ac364cb08dc2d6a5c4318c1182cb1d02274029d590d"},
+    {file = "msgpack-1.0.7-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:b573a43ef7c368ba4ea06050a957c2a7550f729c31f11dd616d2ac4aba99888d"},
+    {file = "msgpack-1.0.7-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:ccf9a39706b604d884d2cb1e27fe973bc55f2890c52f38df742bc1d79ab9f5e1"},
+    {file = "msgpack-1.0.7-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:cb70766519500281815dfd7a87d3a178acf7ce95390544b8c90587d76b227681"},
+    {file = "msgpack-1.0.7-cp310-cp310-win32.whl", hash = "sha256:b610ff0f24e9f11c9ae653c67ff8cc03c075131401b3e5ef4b82570d1728f8a9"},
+    {file = "msgpack-1.0.7-cp310-cp310-win_amd64.whl", hash = "sha256:a40821a89dc373d6427e2b44b572efc36a2778d3f543299e2f24eb1a5de65415"},
+    {file = "msgpack-1.0.7-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:576eb384292b139821c41995523654ad82d1916da6a60cff129c715a6223ea84"},
+    {file = "msgpack-1.0.7-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:730076207cb816138cf1af7f7237b208340a2c5e749707457d70705715c93b93"},
+    {file = "msgpack-1.0.7-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:85765fdf4b27eb5086f05ac0491090fc76f4f2b28e09d9350c31aac25a5aaff8"},
+    {file = "msgpack-1.0.7-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3476fae43db72bd11f29a5147ae2f3cb22e2f1a91d575ef130d2bf49afd21c46"},
+    {file = "msgpack-1.0.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6d4c80667de2e36970ebf74f42d1088cc9ee7ef5f4e8c35eee1b40eafd33ca5b"},
+    {file = "msgpack-1.0.7-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5b0bf0effb196ed76b7ad883848143427a73c355ae8e569fa538365064188b8e"},
+    {file = "msgpack-1.0.7-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:f9a7c509542db4eceed3dcf21ee5267ab565a83555c9b88a8109dcecc4709002"},
+    {file = "msgpack-1.0.7-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:84b0daf226913133f899ea9b30618722d45feffa67e4fe867b0b5ae83a34060c"},
+    {file = "msgpack-1.0.7-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:ec79ff6159dffcc30853b2ad612ed572af86c92b5168aa3fc01a67b0fa40665e"},
+    {file = "msgpack-1.0.7-cp311-cp311-win32.whl", hash = "sha256:3e7bf4442b310ff154b7bb9d81eb2c016b7d597e364f97d72b1acc3817a0fdc1"},
+    {file = "msgpack-1.0.7-cp311-cp311-win_amd64.whl", hash = "sha256:3f0c8c6dfa6605ab8ff0611995ee30d4f9fcff89966cf562733b4008a3d60d82"},
+    {file = "msgpack-1.0.7-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:f0936e08e0003f66bfd97e74ee530427707297b0d0361247e9b4f59ab78ddc8b"},
+    {file = "msgpack-1.0.7-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:98bbd754a422a0b123c66a4c341de0474cad4a5c10c164ceed6ea090f3563db4"},
+    {file = "msgpack-1.0.7-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:b291f0ee7961a597cbbcc77709374087fa2a9afe7bdb6a40dbbd9b127e79afee"},
+    {file = "msgpack-1.0.7-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ebbbba226f0a108a7366bf4b59bf0f30a12fd5e75100c630267d94d7f0ad20e5"},
+    {file = "msgpack-1.0.7-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1e2d69948e4132813b8d1131f29f9101bc2c915f26089a6d632001a5c1349672"},
+    {file = "msgpack-1.0.7-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bdf38ba2d393c7911ae989c3bbba510ebbcdf4ecbdbfec36272abe350c454075"},
+    {file = "msgpack-1.0.7-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:993584fc821c58d5993521bfdcd31a4adf025c7d745bbd4d12ccfecf695af5ba"},
+    {file = "msgpack-1.0.7-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:52700dc63a4676669b341ba33520f4d6e43d3ca58d422e22ba66d1736b0a6e4c"},
+    {file = "msgpack-1.0.7-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e45ae4927759289c30ccba8d9fdce62bb414977ba158286b5ddaf8df2cddb5c5"},
+    {file = "msgpack-1.0.7-cp312-cp312-win32.whl", hash = "sha256:27dcd6f46a21c18fa5e5deed92a43d4554e3df8d8ca5a47bf0615d6a5f39dbc9"},
+    {file = "msgpack-1.0.7-cp312-cp312-win_amd64.whl", hash = "sha256:7687e22a31e976a0e7fc99c2f4d11ca45eff652a81eb8c8085e9609298916dcf"},
+    {file = "msgpack-1.0.7-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:5b6ccc0c85916998d788b295765ea0e9cb9aac7e4a8ed71d12e7d8ac31c23c95"},
+    {file = "msgpack-1.0.7-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:235a31ec7db685f5c82233bddf9858748b89b8119bf4538d514536c485c15fe0"},
+    {file = "msgpack-1.0.7-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:cab3db8bab4b7e635c1c97270d7a4b2a90c070b33cbc00c99ef3f9be03d3e1f7"},
+    {file = "msgpack-1.0.7-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0bfdd914e55e0d2c9e1526de210f6fe8ffe9705f2b1dfcc4aecc92a4cb4b533d"},
+    {file = "msgpack-1.0.7-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:36e17c4592231a7dbd2ed09027823ab295d2791b3b1efb2aee874b10548b7524"},
+    {file = "msgpack-1.0.7-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:38949d30b11ae5f95c3c91917ee7a6b239f5ec276f271f28638dec9156f82cfc"},
+    {file = "msgpack-1.0.7-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:ff1d0899f104f3921d94579a5638847f783c9b04f2d5f229392ca77fba5b82fc"},
+    {file = "msgpack-1.0.7-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:dc43f1ec66eb8440567186ae2f8c447d91e0372d793dfe8c222aec857b81a8cf"},
+    {file = "msgpack-1.0.7-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:dd632777ff3beaaf629f1ab4396caf7ba0bdd075d948a69460d13d44357aca4c"},
+    {file = "msgpack-1.0.7-cp38-cp38-win32.whl", hash = "sha256:4e71bc4416de195d6e9b4ee93ad3f2f6b2ce11d042b4d7a7ee00bbe0358bd0c2"},
+    {file = "msgpack-1.0.7-cp38-cp38-win_amd64.whl", hash = "sha256:8f5b234f567cf76ee489502ceb7165c2a5cecec081db2b37e35332b537f8157c"},
+    {file = "msgpack-1.0.7-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:bfef2bb6ef068827bbd021017a107194956918ab43ce4d6dc945ffa13efbc25f"},
+    {file = "msgpack-1.0.7-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:484ae3240666ad34cfa31eea7b8c6cd2f1fdaae21d73ce2974211df099a95d81"},
+    {file = "msgpack-1.0.7-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3967e4ad1aa9da62fd53e346ed17d7b2e922cba5ab93bdd46febcac39be636fc"},
+    {file = "msgpack-1.0.7-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8dd178c4c80706546702c59529ffc005681bd6dc2ea234c450661b205445a34d"},
+    {file = "msgpack-1.0.7-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f6ffbc252eb0d229aeb2f9ad051200668fc3a9aaa8994e49f0cb2ffe2b7867e7"},
+    {file = "msgpack-1.0.7-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:822ea70dc4018c7e6223f13affd1c5c30c0f5c12ac1f96cd8e9949acddb48a61"},
+    {file = "msgpack-1.0.7-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:384d779f0d6f1b110eae74cb0659d9aa6ff35aaf547b3955abf2ab4c901c4819"},
+    {file = "msgpack-1.0.7-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:f64e376cd20d3f030190e8c32e1c64582eba56ac6dc7d5b0b49a9d44021b52fd"},
+    {file = "msgpack-1.0.7-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:5ed82f5a7af3697b1c4786053736f24a0efd0a1b8a130d4c7bfee4b9ded0f08f"},
+    {file = "msgpack-1.0.7-cp39-cp39-win32.whl", hash = "sha256:f26a07a6e877c76a88e3cecac8531908d980d3d5067ff69213653649ec0f60ad"},
+    {file = "msgpack-1.0.7-cp39-cp39-win_amd64.whl", hash = "sha256:1dc93e8e4653bdb5910aed79f11e165c85732067614f180f70534f056da97db3"},
+    {file = "msgpack-1.0.7.tar.gz", hash = "sha256:572efc93db7a4d27e404501975ca6d2d9775705c2d922390d878fcf768d92c87"},
+]
+
+[[package]]
+name = "networkx"
+version = "3.2.1"
+description = "Python package for creating and manipulating graphs and networks"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "networkx-3.2.1-py3-none-any.whl", hash = "sha256:f18c69adc97877c42332c170849c96cefa91881c99a7cb3e95b7c659ebdc1ec2"},
+    {file = "networkx-3.2.1.tar.gz", hash = "sha256:9f1bb5cf3409bf324e0a722c20bdb4c20ee39bf1c30ce8ae499c8502b0b5e0c6"},
+]
+
+[package.extras]
+default = ["matplotlib (>=3.5)", "numpy (>=1.22)", "pandas (>=1.4)", "scipy (>=1.9,!=1.11.0,!=1.11.1)"]
+developer = ["changelist (==0.4)", "mypy (>=1.1)", "pre-commit (>=3.2)", "rtoml"]
+doc = ["nb2plots (>=0.7)", "nbconvert (<7.9)", "numpydoc (>=1.6)", "pillow (>=9.4)", "pydata-sphinx-theme (>=0.14)", "sphinx (>=7)", "sphinx-gallery (>=0.14)", "texext (>=0.6.7)"]
+extra = ["lxml (>=4.6)", "pydot (>=1.4.2)", "pygraphviz (>=1.11)", "sympy (>=1.10)"]
+test = ["pytest (>=7.2)", "pytest-cov (>=4.0)"]
+
+[[package]]
+name = "numba"
+version = "0.59.0rc1"
+description = "compiling Python code using LLVM"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "numba-0.59.0rc1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:223453e03b74b68501f4a44ee307641272f1043d204ae3659876ba904e3b76b5"},
+    {file = "numba-0.59.0rc1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:09abefa927fe0546e28e1ab122891955fdc3cea20be02746be58fb36820ba866"},
+    {file = "numba-0.59.0rc1-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ca4eabebae0e60954e54b5f368b5973ff49e3c8dcd838164514b1bbbb48e7538"},
+    {file = "numba-0.59.0rc1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:a7c49fde29fc5acfcd8278d61923fa0d6976141c2cfed8f13e582eaad598ded8"},
+    {file = "numba-0.59.0rc1-cp310-cp310-win_amd64.whl", hash = "sha256:325b3594b5a329d3bf2acc4560a9d9f4d88042a80693e3e8c5d73270579ab8df"},
+    {file = "numba-0.59.0rc1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:2ef2394d24a167e3137b9ec660172d111ffb8cf7718309ea90910b58fa64f60b"},
+    {file = "numba-0.59.0rc1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:1947f78473fc7a093e27e02b9d401a70b6b329a6cb5b75e14ad456e97e54fa56"},
+    {file = "numba-0.59.0rc1-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:468b04c17d6276b2388b15ac45f08f55fcc692d308d7025d1e1143d3e6ed8da6"},
+    {file = "numba-0.59.0rc1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:280614e933df0177e65f1b436ed456b771fab456140627f4f3d5d04e345d76b2"},
+    {file = "numba-0.59.0rc1-cp311-cp311-win_amd64.whl", hash = "sha256:837d4ac751ace4549e47af793e46914d5b69eb7b94509417cdf61cd557f86293"},
+    {file = "numba-0.59.0rc1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:0fcfdbc2e0a038842663b665c4a0c93051beb2742c01346ae2d843f50e6d4a78"},
+    {file = "numba-0.59.0rc1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:07d76dbecca1e05b788b1055892f2d352ff907f3b84a5100caebee6ed09e7747"},
+    {file = "numba-0.59.0rc1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:896de500ef113ee9647fb8c444338bdc9d45e910663da2a102bbc62818427eb4"},
+    {file = "numba-0.59.0rc1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:4238babbee60ebea23f3765e6e632bccd1461b4eb3d3b047c21fa0d0bb2d40da"},
+    {file = "numba-0.59.0rc1-cp312-cp312-win_amd64.whl", hash = "sha256:5610ad0b433053d729d9b4b4cbb1671a5f86429ba047d4185dccc17877095133"},
+    {file = "numba-0.59.0rc1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:d54088cb6afd6a215e897b0a99d8926ca740fa8c1683372f41f7c4ffeb3e378f"},
+    {file = "numba-0.59.0rc1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:d17e27539a3bfcafef066bcc010858fcca26bb2d09771b9a1e63b79986ceeb73"},
+    {file = "numba-0.59.0rc1-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:dca6d67f48fcaceb02a0f2cd808822d7bda7fb493b4559dafdf1035e836031c0"},
+    {file = "numba-0.59.0rc1-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:a7afb719faaf1437580808ca1f13e9ffea21c941ceccca2e59a8ab6aafac205d"},
+    {file = "numba-0.59.0rc1-cp39-cp39-win_amd64.whl", hash = "sha256:3a0de1a45cd4e13b47988c1539dacca023b9b9833ce32f706a4ecc5de165a229"},
+    {file = "numba-0.59.0rc1.tar.gz", hash = "sha256:c8aab21a34081f0c659890d9e49fda42e537d782f6a90c046280c6eae2069d78"},
+]
+
+[package.dependencies]
+llvmlite = "==0.42.*"
+numpy = ">=1.22,<1.27"
+
+[[package]]
+name = "numpy"
+version = "1.26.3"
+description = "Fundamental package for array computing in Python"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "numpy-1.26.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:806dd64230dbbfaca8a27faa64e2f414bf1c6622ab78cc4264f7f5f028fee3bf"},
+    {file = "numpy-1.26.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:02f98011ba4ab17f46f80f7f8f1c291ee7d855fcef0a5a98db80767a468c85cd"},
+    {file = "numpy-1.26.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6d45b3ec2faed4baca41c76617fcdcfa4f684ff7a151ce6fc78ad3b6e85af0a6"},
+    {file = "numpy-1.26.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bdd2b45bf079d9ad90377048e2747a0c82351989a2165821f0c96831b4a2a54b"},
+    {file = "numpy-1.26.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:211ddd1e94817ed2d175b60b6374120244a4dd2287f4ece45d49228b4d529178"},
+    {file = "numpy-1.26.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b1240f767f69d7c4c8a29adde2310b871153df9b26b5cb2b54a561ac85146485"},
+    {file = "numpy-1.26.3-cp310-cp310-win32.whl", hash = "sha256:21a9484e75ad018974a2fdaa216524d64ed4212e418e0a551a2d83403b0531d3"},
+    {file = "numpy-1.26.3-cp310-cp310-win_amd64.whl", hash = "sha256:9e1591f6ae98bcfac2a4bbf9221c0b92ab49762228f38287f6eeb5f3f55905ce"},
+    {file = "numpy-1.26.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b831295e5472954104ecb46cd98c08b98b49c69fdb7040483aff799a755a7374"},
+    {file = "numpy-1.26.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:9e87562b91f68dd8b1c39149d0323b42e0082db7ddb8e934ab4c292094d575d6"},
+    {file = "numpy-1.26.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8c66d6fec467e8c0f975818c1796d25c53521124b7cfb760114be0abad53a0a2"},
+    {file = "numpy-1.26.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f25e2811a9c932e43943a2615e65fc487a0b6b49218899e62e426e7f0a57eeda"},
+    {file = "numpy-1.26.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:af36e0aa45e25c9f57bf684b1175e59ea05d9a7d3e8e87b7ae1a1da246f2767e"},
+    {file = "numpy-1.26.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:51c7f1b344f302067b02e0f5b5d2daa9ed4a721cf49f070280ac202738ea7f00"},
+    {file = "numpy-1.26.3-cp311-cp311-win32.whl", hash = "sha256:7ca4f24341df071877849eb2034948459ce3a07915c2734f1abb4018d9c49d7b"},
+    {file = "numpy-1.26.3-cp311-cp311-win_amd64.whl", hash = "sha256:39763aee6dfdd4878032361b30b2b12593fb445ddb66bbac802e2113eb8a6ac4"},
+    {file = "numpy-1.26.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:a7081fd19a6d573e1a05e600c82a1c421011db7935ed0d5c483e9dd96b99cf13"},
+    {file = "numpy-1.26.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:12c70ac274b32bc00c7f61b515126c9205323703abb99cd41836e8125ea0043e"},
+    {file = "numpy-1.26.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7f784e13e598e9594750b2ef6729bcd5a47f6cfe4a12cca13def35e06d8163e3"},
+    {file = "numpy-1.26.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5f24750ef94d56ce6e33e4019a8a4d68cfdb1ef661a52cdaee628a56d2437419"},
+    {file = "numpy-1.26.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:77810ef29e0fb1d289d225cabb9ee6cf4d11978a00bb99f7f8ec2132a84e0166"},
+    {file = "numpy-1.26.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8ed07a90f5450d99dad60d3799f9c03c6566709bd53b497eb9ccad9a55867f36"},
+    {file = "numpy-1.26.3-cp312-cp312-win32.whl", hash = "sha256:f73497e8c38295aaa4741bdfa4fda1a5aedda5473074369eca10626835445511"},
+    {file = "numpy-1.26.3-cp312-cp312-win_amd64.whl", hash = "sha256:da4b0c6c699a0ad73c810736303f7fbae483bcb012e38d7eb06a5e3b432c981b"},
+    {file = "numpy-1.26.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:1666f634cb3c80ccbd77ec97bc17337718f56d6658acf5d3b906ca03e90ce87f"},
+    {file = "numpy-1.26.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:18c3319a7d39b2c6a9e3bb75aab2304ab79a811ac0168a671a62e6346c29b03f"},
+    {file = "numpy-1.26.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0b7e807d6888da0db6e7e75838444d62495e2b588b99e90dd80c3459594e857b"},
+    {file = "numpy-1.26.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b4d362e17bcb0011738c2d83e0a65ea8ce627057b2fdda37678f4374a382a137"},
+    {file = "numpy-1.26.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:b8c275f0ae90069496068c714387b4a0eba5d531aace269559ff2b43655edd58"},
+    {file = "numpy-1.26.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:cc0743f0302b94f397a4a65a660d4cd24267439eb16493fb3caad2e4389bccbb"},
+    {file = "numpy-1.26.3-cp39-cp39-win32.whl", hash = "sha256:9bc6d1a7f8cedd519c4b7b1156d98e051b726bf160715b769106661d567b3f03"},
+    {file = "numpy-1.26.3-cp39-cp39-win_amd64.whl", hash = "sha256:867e3644e208c8922a3be26fc6bbf112a035f50f0a86497f98f228c50c607bb2"},
+    {file = "numpy-1.26.3-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:3c67423b3703f8fbd90f5adaa37f85b5794d3366948efe9a5190a5f3a83fc34e"},
+    {file = "numpy-1.26.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:46f47ee566d98849323f01b349d58f2557f02167ee301e5e28809a8c0e27a2d0"},
+    {file = "numpy-1.26.3-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:a8474703bffc65ca15853d5fd4d06b18138ae90c17c8d12169968e998e448bb5"},
+    {file = "numpy-1.26.3.tar.gz", hash = "sha256:697df43e2b6310ecc9d95f05d5ef20eacc09c7c4ecc9da3f235d39e71b7da1e4"},
+]
+
+[[package]]
+name = "nvidia-cublas-cu12"
+version = "12.1.3.1"
+description = "CUBLAS native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl", hash = "sha256:ee53ccca76a6fc08fb9701aa95b6ceb242cdaab118c3bb152af4e579af792728"},
+    {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-win_amd64.whl", hash = "sha256:2b964d60e8cf11b5e1073d179d85fa340c120e99b3067558f3cf98dd69d02906"},
+]
+
+[[package]]
+name = "nvidia-cuda-cupti-cu12"
+version = "12.1.105"
+description = "CUDA profiling tools runtime libs."
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:e54fde3983165c624cb79254ae9818a456eb6e87a7fd4d56a2352c24ee542d7e"},
+    {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:bea8236d13a0ac7190bd2919c3e8e6ce1e402104276e6f9694479e48bb0eb2a4"},
+]
+
+[[package]]
+name = "nvidia-cuda-nvrtc-cu12"
+version = "12.1.105"
+description = "NVRTC native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:339b385f50c309763ca65456ec75e17bbefcbbf2893f462cb8b90584cd27a1c2"},
+    {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:0a98a522d9ff138b96c010a65e145dc1b4850e9ecb75a0172371793752fd46ed"},
+]
+
+[[package]]
+name = "nvidia-cuda-runtime-cu12"
+version = "12.1.105"
+description = "CUDA Runtime native Libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:6e258468ddf5796e25f1dc591a31029fa317d97a0a94ed93468fc86301d61e40"},
+    {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:dfb46ef84d73fababab44cf03e3b83f80700d27ca300e537f85f636fac474344"},
+]
+
+[[package]]
+name = "nvidia-cudnn-cu12"
+version = "8.9.2.26"
+description = "cuDNN runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl", hash = "sha256:5ccb288774fdfb07a7e7025ffec286971c06d8d7b4fb162525334616d7629ff9"},
+]
+
+[package.dependencies]
+nvidia-cublas-cu12 = "*"
+
+[[package]]
+name = "nvidia-cufft-cu12"
+version = "11.0.2.54"
+description = "CUFFT native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl", hash = "sha256:794e3948a1aa71fd817c3775866943936774d1c14e7628c74f6f7417224cdf56"},
+    {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-win_amd64.whl", hash = "sha256:d9ac353f78ff89951da4af698f80870b1534ed69993f10a4cf1d96f21357e253"},
+]
+
+[[package]]
+name = "nvidia-curand-cu12"
+version = "10.3.2.106"
+description = "CURAND native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:9d264c5036dde4e64f1de8c50ae753237c12e0b1348738169cd0f8a536c0e1e0"},
+    {file = "nvidia_curand_cu12-10.3.2.106-py3-none-win_amd64.whl", hash = "sha256:75b6b0c574c0037839121317e17fd01f8a69fd2ef8e25853d826fec30bdba74a"},
+]
+
+[[package]]
+name = "nvidia-cusolver-cu12"
+version = "11.4.5.107"
+description = "CUDA solver native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl", hash = "sha256:8a7ec542f0412294b15072fa7dab71d31334014a69f953004ea7a118206fe0dd"},
+    {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-win_amd64.whl", hash = "sha256:74e0c3a24c78612192a74fcd90dd117f1cf21dea4822e66d89e8ea80e3cd2da5"},
+]
+
+[package.dependencies]
+nvidia-cublas-cu12 = "*"
+nvidia-cusparse-cu12 = "*"
+nvidia-nvjitlink-cu12 = "*"
+
+[[package]]
+name = "nvidia-cusparse-cu12"
+version = "12.1.0.106"
+description = "CUSPARSE native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:f3b50f42cf363f86ab21f720998517a659a48131e8d538dc02f8768237bd884c"},
+    {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-win_amd64.whl", hash = "sha256:b798237e81b9719373e8fae8d4f091b70a0cf09d9d85c95a557e11df2d8e9a5a"},
+]
+
+[package.dependencies]
+nvidia-nvjitlink-cu12 = "*"
+
+[[package]]
+name = "nvidia-nccl-cu12"
+version = "2.18.1"
+description = "NVIDIA Collective Communication Library (NCCL) Runtime"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_nccl_cu12-2.18.1-py3-none-manylinux1_x86_64.whl", hash = "sha256:1a6c4acefcbebfa6de320f412bf7866de856e786e0462326ba1bac40de0b5e71"},
+]
+
+[[package]]
+name = "nvidia-nvjitlink-cu12"
+version = "12.3.101"
+description = "Nvidia JIT LTO Library"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_nvjitlink_cu12-12.3.101-py3-none-manylinux1_x86_64.whl", hash = "sha256:64335a8088e2b9d196ae8665430bc6a2b7e6ef2eb877a9c735c804bd4ff6467c"},
+    {file = "nvidia_nvjitlink_cu12-12.3.101-py3-none-win_amd64.whl", hash = "sha256:1b2e317e437433753530792f13eece58f0aec21a2b05903be7bffe58a606cbd1"},
+]
+
+[[package]]
+name = "nvidia-nvtx-cu12"
+version = "12.1.105"
+description = "NVIDIA Tools Extension"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:dc21cf308ca5691e7c04d962e213f8a4aa9bbfa23d95412f452254c2caeb09e5"},
+    {file = "nvidia_nvtx_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:65f4d98982b31b60026e0e6de73fbdfc09d08a96f4656dd3665ca616a11e1e82"},
+]
+
+[[package]]
+name = "omegaconf"
+version = "2.3.0"
+description = "A flexible configuration library"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "omegaconf-2.3.0-py3-none-any.whl", hash = "sha256:7b4df175cdb08ba400f45cae3bdcae7ba8365db4d165fc65fd04b050ab63b46b"},
+    {file = "omegaconf-2.3.0.tar.gz", hash = "sha256:d5d4b6d29955cc50ad50c46dc269bcd92c6e00f5f90d23ab5fee7bfca4ba4cc7"},
+]
+
+[package.dependencies]
+antlr4-python3-runtime = "==4.9.*"
+PyYAML = ">=5.1.0"
+
+[[package]]
+name = "packaging"
+version = "23.2"
+description = "Core utilities for Python packages"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "packaging-23.2-py3-none-any.whl", hash = "sha256:8c491190033a9af7e1d931d0b5dacc2ef47509b34dd0de67ed209b5203fc88c7"},
+    {file = "packaging-23.2.tar.gz", hash = "sha256:048fb0e9405036518eaaf48a55953c750c11e1a1b68e0dd1a9d62ed0c092cfc5"},
+]
+
+[[package]]
+name = "pastel"
+version = "0.2.1"
+description = "Bring colors to your terminal."
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+files = [
+    {file = "pastel-0.2.1-py2.py3-none-any.whl", hash = "sha256:4349225fcdf6c2bb34d483e523475de5bb04a5c10ef711263452cb37d7dd4364"},
+    {file = "pastel-0.2.1.tar.gz", hash = "sha256:e6581ac04e973cac858828c6202c1e1e81fee1dc7de7683f3e1ffe0bfd8a573d"},
+]
+
+[[package]]
+name = "platformdirs"
+version = "4.1.0"
+description = "A small Python package for determining appropriate platform-specific dirs, e.g. a \"user data dir\"."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "platformdirs-4.1.0-py3-none-any.whl", hash = "sha256:11c8f37bcca40db96d8144522d925583bdb7a31f7b0e37e3ed4318400a8e2380"},
+    {file = "platformdirs-4.1.0.tar.gz", hash = "sha256:906d548203468492d432bcb294d4bc2fff751bf84971fbb2c10918cc206ee420"},
+]
+
+[package.extras]
+docs = ["furo (>=2023.7.26)", "proselint (>=0.13)", "sphinx (>=7.1.1)", "sphinx-autodoc-typehints (>=1.24)"]
+test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=7.4)", "pytest-cov (>=4.1)", "pytest-mock (>=3.11.1)"]
+
+[[package]]
+name = "poethepoet"
+version = "0.24.4"
+description = "A task runner that works well with poetry."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "poethepoet-0.24.4-py3-none-any.whl", hash = "sha256:fb4ea35d7f40fe2081ea917d2e4102e2310fda2cde78974050ca83896e229075"},
+    {file = "poethepoet-0.24.4.tar.gz", hash = "sha256:ff4220843a87c888cbcb5312c8905214701d0af60ac7271795baa8369b428fef"},
+]
+
+[package.dependencies]
+pastel = ">=0.2.1,<0.3.0"
+tomli = ">=1.2.2"
+
+[package.extras]
+poetry-plugin = ["poetry (>=1.0,<2.0)"]
+
+[[package]]
+name = "pooch"
+version = "1.8.0"
+description = "\"Pooch manages your Python library's sample data files: it automatically downloads and stores them in a local directory, with support for versioning and corruption checks.\""
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "pooch-1.8.0-py3-none-any.whl", hash = "sha256:1bfba436d9e2ad5199ccad3583cca8c241b8736b5bb23fe67c213d52650dbb66"},
+    {file = "pooch-1.8.0.tar.gz", hash = "sha256:f59981fd5b9b5d032dcde8f4a11eaa492c2ac6343fae3596a2fdae35fc54b0a0"},
+]
+
+[package.dependencies]
+packaging = ">=20.0"
+platformdirs = ">=2.5.0"
+requests = ">=2.19.0"
+
+[package.extras]
+progress = ["tqdm (>=4.41.0,<5.0.0)"]
+sftp = ["paramiko (>=2.7.0)"]
+xxhash = ["xxhash (>=1.4.3)"]
+
+[[package]]
+name = "portalocker"
+version = "2.8.2"
+description = "Wraps the portalocker recipe for easy usage"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "portalocker-2.8.2-py3-none-any.whl", hash = "sha256:cfb86acc09b9aa7c3b43594e19be1345b9d16af3feb08bf92f23d4dce513a28e"},
+    {file = "portalocker-2.8.2.tar.gz", hash = "sha256:2b035aa7828e46c58e9b31390ee1f169b98e1066ab10b9a6a861fe7e25ee4f33"},
+]
+
+[package.dependencies]
+pywin32 = {version = ">=226", markers = "platform_system == \"Windows\""}
+
+[package.extras]
+docs = ["sphinx (>=1.7.1)"]
+redis = ["redis"]
+tests = ["pytest (>=5.4.1)", "pytest-cov (>=2.8.1)", "pytest-mypy (>=0.8.0)", "pytest-timeout (>=2.1.0)", "redis", "sphinx (>=6.0.0)", "types-redis"]
+
+[[package]]
+name = "praat-parselmouth"
+version = "0.4.3"
+description = "Praat in Python, the Pythonic way"
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,>=2.7"
+files = [
+    {file = "praat-parselmouth-0.4.3.tar.gz", hash = "sha256:93538d0ba06444b68d18b793efb436b0d645c62c0397c4977c1d27b679aee168"},
+    {file = "praat_parselmouth-0.4.3-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:124925f3e40a6d626d65789d449bdabe43078528efbee6f3a1df6e67db60c971"},
+    {file = "praat_parselmouth-0.4.3-cp27-cp27m-manylinux2010_i686.whl", hash = "sha256:0d3023d9b625c6b0a3cbe8a4f09cc23f666f9b9df40c59e33c4c9ca5b8ea1dac"},
+    {file = "praat_parselmouth-0.4.3-cp27-cp27m-manylinux2010_x86_64.whl", hash = "sha256:6841b9d9d2a614382cf186311610d663f0170ba20824296878eb98905b04899a"},
+    {file = "praat_parselmouth-0.4.3-cp27-cp27m-win32.whl", hash = "sha256:4fee56603cb57326457c6af779b89f96e7b2745114baa996659e1d52e5f245a3"},
+    {file = "praat_parselmouth-0.4.3-cp27-cp27m-win_amd64.whl", hash = "sha256:dc688749a0db4144936d3ed5180996500eb927bbf321192019ddee535fb97f3d"},
+    {file = "praat_parselmouth-0.4.3-cp27-cp27mu-manylinux2010_i686.whl", hash = "sha256:c0ccf73de16c0f69162952b0d1865d4dbc929de0f9b88a9d7aea57f454de3cb8"},
+    {file = "praat_parselmouth-0.4.3-cp27-cp27mu-manylinux2010_x86_64.whl", hash = "sha256:87fa2dd7f8b5dd5e3127af82e97b229ae2db8e1656525329224df4c0bffa024c"},
+    {file = "praat_parselmouth-0.4.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:2bc111055efccf2bb25039a7891ec9ef106b13ddc5680293659ff0b4c5f4353f"},
+    {file = "praat_parselmouth-0.4.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:cd38542210b1f381086b4a9424832b2330c42712e0fb7ea6c28c9200119c294b"},
+    {file = "praat_parselmouth-0.4.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a536b37411c52171500984c97bfd66dc000701a7dc0807e11061b85a653a600a"},
+    {file = "praat_parselmouth-0.4.3-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6ea1ab0632eff129516f147041aaf7874e50770561a2e9b9c81913b6de243f2a"},
+    {file = "praat_parselmouth-0.4.3-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:543ba3deb32502e93074b76b1cfb3f09e598e5d9f74a0345fa5b3928fedb5a51"},
+    {file = "praat_parselmouth-0.4.3-cp310-cp310-win32.whl", hash = "sha256:e0addf774a57d57a54df2b06de04ad0de34e81a3abfda03f744c732776c779ec"},
+    {file = "praat_parselmouth-0.4.3-cp310-cp310-win_amd64.whl", hash = "sha256:fc497357aeea2e3cbca2fb308d66b9de9739dc6b320ca2661ca6250f7a7489bd"},
+    {file = "praat_parselmouth-0.4.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:afac52cb7a72cda7fe2ec1d9573d8f402786abcb06bd7a22f2ca240f95e33263"},
+    {file = "praat_parselmouth-0.4.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b2261a79c2dc5387a7a678ec304ef8dd00ed93d9e028148bbb064fd0ac222a3a"},
+    {file = "praat_parselmouth-0.4.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:de31b458d3c1ca7ee45506871a38fdc3aec44526c065552adf8bec2876e816bd"},
+    {file = "praat_parselmouth-0.4.3-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:63ff24e045bed7c44f140fb7bab910d89fd3a45b7e8afe5b5e936aa2eea62904"},
+    {file = "praat_parselmouth-0.4.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a40c51c628235c54c8956306fc58fd14cd04127d85359134ef73ef35ff19d651"},
+    {file = "praat_parselmouth-0.4.3-cp311-cp311-win32.whl", hash = "sha256:f8ad9ee3be60d33f1ad593ec5f99466b1c266e00d29a5ec5787f969c618a7a9a"},
+    {file = "praat_parselmouth-0.4.3-cp311-cp311-win_amd64.whl", hash = "sha256:c32b1f3632e69ed67f501c635fff37ad72e1eae4ddd1c2c0827c4690c06ee990"},
+    {file = "praat_parselmouth-0.4.3-cp35-cp35m-macosx_10_9_x86_64.whl", hash = "sha256:1dcb6f55376f193c83d123953a55de471bcadd756af3b157c13d455b0c052999"},
+    {file = "praat_parselmouth-0.4.3-cp35-cp35m-manylinux2010_i686.whl", hash = "sha256:0970facd26b771f5799a396a0e54d12a69fbf8904a4f6ae0442f3831175e4508"},
+    {file = "praat_parselmouth-0.4.3-cp35-cp35m-manylinux2010_x86_64.whl", hash = "sha256:5c1104f41d9fef48cd44247738b9c8735e10a12ba0a1860e478e0bd69201813e"},
+    {file = "praat_parselmouth-0.4.3-cp35-cp35m-win32.whl", hash = "sha256:3d12469e301d9a25f29f6cb5427aa9a1276e7f2f1edf1a3caede69a84c46170f"},
+    {file = "praat_parselmouth-0.4.3-cp35-cp35m-win_amd64.whl", hash = "sha256:c4142faf664dd6c7f1773d04331b278d92e17064eaaef09132954f72a9041ea0"},
+    {file = "praat_parselmouth-0.4.3-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:5ea2079d519e8d42ed8d2de3c4f68803110060a8ae5d1c56df795c600aa1c3be"},
+    {file = "praat_parselmouth-0.4.3-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:2e88f00b740548cf3de5768b2d06e296e525164ea71ccc991920f41f2e277ad2"},
+    {file = "praat_parselmouth-0.4.3-cp36-cp36m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:2da226bccd52fd81223eb94a7ea43a1a7588e4384ea65ce0818329b73ef8df6d"},
+    {file = "praat_parselmouth-0.4.3-cp36-cp36m-win32.whl", hash = "sha256:0f3af0413992398ac613b0eefdfbcb8cad064c36a28b972300a2bb760523c109"},
+    {file = "praat_parselmouth-0.4.3-cp36-cp36m-win_amd64.whl", hash = "sha256:e0ed79941b6e37a440860511767eedd85ec003060870d10ff1f98773b2a268ae"},
+    {file = "praat_parselmouth-0.4.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:10f3113ad4f5f6df5fe81d4080ca3ad46de2fe0fdb8ebbcad1ba884b1cae3b9d"},
+    {file = "praat_parselmouth-0.4.3-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6e9338f7a1b304390014bb2eec619e5a306527a4df438e68439c92aa968627dc"},
+    {file = "praat_parselmouth-0.4.3-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:cb3798b2ca8163444662b6ae84a74b1add38b2c04e5af8d07bde55cf0335300a"},
+    {file = "praat_parselmouth-0.4.3-cp37-cp37m-win32.whl", hash = "sha256:d947f9d1fb092b91acca1259ce4dd62ff4f456338958fd1fd41ee65efc53ca2c"},
+    {file = "praat_parselmouth-0.4.3-cp37-cp37m-win_amd64.whl", hash = "sha256:2f3e026f590aeec8f68921359f56a42efa43076942f271244bee57fd22db8eef"},
+    {file = "praat_parselmouth-0.4.3-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:28844229dab2a9335629b4526188b9540d02208856f48b1a46776279c022f937"},
+    {file = "praat_parselmouth-0.4.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:410748af84eb8c2eb69e408e300694a45090ed7c4f31375c4ec75a8c18f87169"},
+    {file = "praat_parselmouth-0.4.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:30ff6f17babad25b9d6ab086465a54494eef9d1b4368b0722230c5282be2bf94"},
+    {file = "praat_parselmouth-0.4.3-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:ff7096bc3e87a8f719e66f5e16a90e2f6de445612abd234f86837d390b947421"},
+    {file = "praat_parselmouth-0.4.3-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:f41d121c4d2322ff12808bb2c4490609f750f89064170e327dfd74fca13cc212"},
+    {file = "praat_parselmouth-0.4.3-cp38-cp38-win32.whl", hash = "sha256:9af9945db11fab0e1ed29ad20f7c97a3e7a8d016328ad6d7237a0d7819db075e"},
+    {file = "praat_parselmouth-0.4.3-cp38-cp38-win_amd64.whl", hash = "sha256:ae0c63c432e8216d7c70da44131f51c845fb81d48ac04eb5f39ebcfae34624be"},
+    {file = "praat_parselmouth-0.4.3-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:8e25658af5a87ed502753de6924c51bf3400d4078e67a611b5874ab08b478fdb"},
+    {file = "praat_parselmouth-0.4.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:7aa2ffd0c6e47feda35343a9d6722b2558f3677a4a51bf5ec864f27ab80e2f42"},
+    {file = "praat_parselmouth-0.4.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3b245d9457ab39f12142da160cda12c4c2a58d9b916e5bb33e6b3ac267882d46"},
+    {file = "praat_parselmouth-0.4.3-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:da9779a694941074bc5b199dd3cb41ad4af3306552f06af8dbfdea6ab0a87dec"},
+    {file = "praat_parselmouth-0.4.3-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:cfa141c04fd8a0477f91c168878112098a25cbac7ac4a20de627bc9293ee4667"},
+    {file = "praat_parselmouth-0.4.3-cp39-cp39-win32.whl", hash = "sha256:6941fe602802fd57ecbedecd612b41493b7d1c6bf722ac0cbf3f47f805fbbd43"},
+    {file = "praat_parselmouth-0.4.3-cp39-cp39-win_amd64.whl", hash = "sha256:5252496e0391754a642973837670c56ecd39c8e0a1f7ec6e6b60b0cd2cc9f51d"},
+    {file = "praat_parselmouth-0.4.3-pp27-pypy_73-macosx_10_9_x86_64.whl", hash = "sha256:fd7c143c6511807b67c92b3ab94733746c0ae3a7b4ba52d6763585c4d459061d"},
+    {file = "praat_parselmouth-0.4.3-pp27-pypy_73-manylinux2010_x86_64.whl", hash = "sha256:7ad0739ad6c102817c7d43b67b7270f78cb431eb72b6ecd9a17e354d1b379deb"},
+    {file = "praat_parselmouth-0.4.3-pp27-pypy_73-win32.whl", hash = "sha256:f5e98ec1f41efba90bedab358cff8e6a3c6473978e1f42b55d0977e580efe673"},
+    {file = "praat_parselmouth-0.4.3-pp36-pypy36_pp73-macosx_10_9_x86_64.whl", hash = "sha256:7b58c1c8fd967446f6d74775b5d9bceadfe35a928fa5f192d4d03d80cb005d92"},
+    {file = "praat_parselmouth-0.4.3-pp36-pypy36_pp73-manylinux2010_x86_64.whl", hash = "sha256:d217df07c770156fa284aff3e7a5c11eb43e37f0226730d729d6b45be8a7c4d7"},
+    {file = "praat_parselmouth-0.4.3-pp36-pypy36_pp73-win32.whl", hash = "sha256:29cb47438989f8155c3b3dca987afd48999dec71e4b79564aa7e922c3c5c1f9a"},
+    {file = "praat_parselmouth-0.4.3-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:5f772b4a097654883f4bba41efae419f9ebdd5e83ef7a857e547100d26663e2c"},
+    {file = "praat_parselmouth-0.4.3-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:bf9634a6986732dc43a88b3a16a0000cff903da1db6556b7959a6a4897f25570"},
+    {file = "praat_parselmouth-0.4.3-pp37-pypy37_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:fab1bbb6a88f47cb5d0db07a4fd6d88b9294d2775a7556aeb459e96ac372e29f"},
+    {file = "praat_parselmouth-0.4.3-pp37-pypy37_pp73-win32.whl", hash = "sha256:261f03f95f25943da2cf746599e47acfcf79b7fc823c871571901d6c97bad948"},
+    {file = "praat_parselmouth-0.4.3-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:199b8df2659a1e6f30e9ae3064b0a28a661d834d2bccb56d22051c40cc348817"},
+    {file = "praat_parselmouth-0.4.3-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ef1f3f6bd08cc410d0d595f6a9c7dd72558e30ad3bd7949c94ea4e07a2de2605"},
+    {file = "praat_parselmouth-0.4.3-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:28a61b7a3cf95a53554dd3ebb4f48e991d4b913ae2d2fbc3868a4e864d69794f"},
+    {file = "praat_parselmouth-0.4.3-pp38-pypy38_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:488833ee33690fa1a57a3c429d286e42e6882748f5c3d28dc50889abec12b8c2"},
+    {file = "praat_parselmouth-0.4.3-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:10f181e199c47fa90fe7cad065275f7f3ccda2de6febf86394cf96aa48531079"},
+    {file = "praat_parselmouth-0.4.3-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:52702bc5cdf59b2b4db87448fe9042307e5ebce6b67ee5ea55c2b8627ce803e0"},
+    {file = "praat_parselmouth-0.4.3-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a7d4f5d7c701517986654365f0a41b8b4a610a2ddc0365da60e48c098774259b"},
+    {file = "praat_parselmouth-0.4.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4dc013608a536ad74efdc3242421cabfcb8cb2e9cd1259ec9de9aeaa141c2d14"},
+    {file = "praat_parselmouth-0.4.3-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:d593065ed1500d305d9cf3d20f5ac7e3671061c3c073ef6e94e97817a664d399"},
+]
+
+[package.dependencies]
+numpy = ">=1.7.0"
+
+[[package]]
+name = "protobuf"
+version = "4.25.2"
+description = ""
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "protobuf-4.25.2-cp310-abi3-win32.whl", hash = "sha256:b50c949608682b12efb0b2717f53256f03636af5f60ac0c1d900df6213910fd6"},
+    {file = "protobuf-4.25.2-cp310-abi3-win_amd64.whl", hash = "sha256:8f62574857ee1de9f770baf04dde4165e30b15ad97ba03ceac65f760ff018ac9"},
+    {file = "protobuf-4.25.2-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:2db9f8fa64fbdcdc93767d3cf81e0f2aef176284071507e3ede160811502fd3d"},
+    {file = "protobuf-4.25.2-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:10894a2885b7175d3984f2be8d9850712c57d5e7587a2410720af8be56cdaf62"},
+    {file = "protobuf-4.25.2-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:fc381d1dd0516343f1440019cedf08a7405f791cd49eef4ae1ea06520bc1c020"},
+    {file = "protobuf-4.25.2-cp38-cp38-win32.whl", hash = "sha256:33a1aeef4b1927431d1be780e87b641e322b88d654203a9e9d93f218ee359e61"},
+    {file = "protobuf-4.25.2-cp38-cp38-win_amd64.whl", hash = "sha256:47f3de503fe7c1245f6f03bea7e8d3ec11c6c4a2ea9ef910e3221c8a15516d62"},
+    {file = "protobuf-4.25.2-cp39-cp39-win32.whl", hash = "sha256:5e5c933b4c30a988b52e0b7c02641760a5ba046edc5e43d3b94a74c9fc57c1b3"},
+    {file = "protobuf-4.25.2-cp39-cp39-win_amd64.whl", hash = "sha256:d66a769b8d687df9024f2985d5137a337f957a0916cf5464d1513eee96a63ff0"},
+    {file = "protobuf-4.25.2-py3-none-any.whl", hash = "sha256:a8b7a98d4ce823303145bf3c1a8bdb0f2f4642a414b196f04ad9853ed0c8f830"},
+    {file = "protobuf-4.25.2.tar.gz", hash = "sha256:fe599e175cb347efc8ee524bcd4b902d11f7262c0e569ececcb89995c15f0a5e"},
+]
+
+[[package]]
+name = "pycparser"
+version = "2.21"
+description = "C parser in Python"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+files = [
+    {file = "pycparser-2.21-py2.py3-none-any.whl", hash = "sha256:8ee45429555515e1f6b185e78100aea234072576aa43ab53aefcae078162fca9"},
+    {file = "pycparser-2.21.tar.gz", hash = "sha256:e644fdec12f7872f86c58ff790da456218b10f863970249516d60a5eaca77206"},
+]
+
+[[package]]
+name = "pydantic"
+version = "2.5.3"
+description = "Data validation using Python type hints"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "pydantic-2.5.3-py3-none-any.whl", hash = "sha256:d0caf5954bee831b6bfe7e338c32b9e30c85dfe080c843680783ac2b631673b4"},
+    {file = "pydantic-2.5.3.tar.gz", hash = "sha256:b3ef57c62535b0941697cce638c08900d87fcb67e29cfa99e8a68f747f393f7a"},
+]
+
+[package.dependencies]
+annotated-types = ">=0.4.0"
+pydantic-core = "2.14.6"
+typing-extensions = ">=4.6.1"
+
+[package.extras]
+email = ["email-validator (>=2.0.0)"]
+
+[[package]]
+name = "pydantic-core"
+version = "2.14.6"
+description = ""
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "pydantic_core-2.14.6-cp310-cp310-macosx_10_7_x86_64.whl", hash = "sha256:72f9a942d739f09cd42fffe5dc759928217649f070056f03c70df14f5770acf9"},
+    {file = "pydantic_core-2.14.6-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:6a31d98c0d69776c2576dda4b77b8e0c69ad08e8b539c25c7d0ca0dc19a50d6c"},
+    {file = "pydantic_core-2.14.6-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5aa90562bc079c6c290f0512b21768967f9968e4cfea84ea4ff5af5d917016e4"},
+    {file = "pydantic_core-2.14.6-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:370ffecb5316ed23b667d99ce4debe53ea664b99cc37bfa2af47bc769056d534"},
+    {file = "pydantic_core-2.14.6-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f85f3843bdb1fe80e8c206fe6eed7a1caeae897e496542cee499c374a85c6e08"},
+    {file = "pydantic_core-2.14.6-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9862bf828112e19685b76ca499b379338fd4c5c269d897e218b2ae8fcb80139d"},
+    {file = "pydantic_core-2.14.6-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:036137b5ad0cb0004c75b579445a1efccd072387a36c7f217bb8efd1afbe5245"},
+    {file = "pydantic_core-2.14.6-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:92879bce89f91f4b2416eba4429c7b5ca22c45ef4a499c39f0c5c69257522c7c"},
+    {file = "pydantic_core-2.14.6-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:0c08de15d50fa190d577e8591f0329a643eeaed696d7771760295998aca6bc66"},
+    {file = "pydantic_core-2.14.6-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:36099c69f6b14fc2c49d7996cbf4f87ec4f0e66d1c74aa05228583225a07b590"},
+    {file = "pydantic_core-2.14.6-cp310-none-win32.whl", hash = "sha256:7be719e4d2ae6c314f72844ba9d69e38dff342bc360379f7c8537c48e23034b7"},
+    {file = "pydantic_core-2.14.6-cp310-none-win_amd64.whl", hash = "sha256:36fa402dcdc8ea7f1b0ddcf0df4254cc6b2e08f8cd80e7010d4c4ae6e86b2a87"},
+    {file = "pydantic_core-2.14.6-cp311-cp311-macosx_10_7_x86_64.whl", hash = "sha256:dea7fcd62915fb150cdc373212141a30037e11b761fbced340e9db3379b892d4"},
+    {file = "pydantic_core-2.14.6-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ffff855100bc066ff2cd3aa4a60bc9534661816b110f0243e59503ec2df38421"},
+    {file = "pydantic_core-2.14.6-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1b027c86c66b8627eb90e57aee1f526df77dc6d8b354ec498be9a757d513b92b"},
+    {file = "pydantic_core-2.14.6-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:00b1087dabcee0b0ffd104f9f53d7d3eaddfaa314cdd6726143af6bc713aa27e"},
+    {file = "pydantic_core-2.14.6-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:75ec284328b60a4e91010c1acade0c30584f28a1f345bc8f72fe8b9e46ec6a96"},
+    {file = "pydantic_core-2.14.6-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7e1f4744eea1501404b20b0ac059ff7e3f96a97d3e3f48ce27a139e053bb370b"},
+    {file = "pydantic_core-2.14.6-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b2602177668f89b38b9f84b7b3435d0a72511ddef45dc14446811759b82235a1"},
+    {file = "pydantic_core-2.14.6-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:6c8edaea3089bf908dd27da8f5d9e395c5b4dc092dbcce9b65e7156099b4b937"},
+    {file = "pydantic_core-2.14.6-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:478e9e7b360dfec451daafe286998d4a1eeaecf6d69c427b834ae771cad4b622"},
+    {file = "pydantic_core-2.14.6-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:b6ca36c12a5120bad343eef193cc0122928c5c7466121da7c20f41160ba00ba2"},
+    {file = "pydantic_core-2.14.6-cp311-none-win32.whl", hash = "sha256:2b8719037e570639e6b665a4050add43134d80b687288ba3ade18b22bbb29dd2"},
+    {file = "pydantic_core-2.14.6-cp311-none-win_amd64.whl", hash = "sha256:78ee52ecc088c61cce32b2d30a826f929e1708f7b9247dc3b921aec367dc1b23"},
+    {file = "pydantic_core-2.14.6-cp311-none-win_arm64.whl", hash = "sha256:a19b794f8fe6569472ff77602437ec4430f9b2b9ec7a1105cfd2232f9ba355e6"},
+    {file = "pydantic_core-2.14.6-cp312-cp312-macosx_10_7_x86_64.whl", hash = "sha256:667aa2eac9cd0700af1ddb38b7b1ef246d8cf94c85637cbb03d7757ca4c3fdec"},
+    {file = "pydantic_core-2.14.6-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:cdee837710ef6b56ebd20245b83799fce40b265b3b406e51e8ccc5b85b9099b7"},
+    {file = "pydantic_core-2.14.6-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2c5bcf3414367e29f83fd66f7de64509a8fd2368b1edf4351e862910727d3e51"},
+    {file = "pydantic_core-2.14.6-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:26a92ae76f75d1915806b77cf459811e772d8f71fd1e4339c99750f0e7f6324f"},
+    {file = "pydantic_core-2.14.6-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a983cca5ed1dd9a35e9e42ebf9f278d344603bfcb174ff99a5815f953925140a"},
+    {file = "pydantic_core-2.14.6-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cb92f9061657287eded380d7dc455bbf115430b3aa4741bdc662d02977e7d0af"},
+    {file = "pydantic_core-2.14.6-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e4ace1e220b078c8e48e82c081e35002038657e4b37d403ce940fa679e57113b"},
+    {file = "pydantic_core-2.14.6-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:ef633add81832f4b56d3b4c9408b43d530dfca29e68fb1b797dcb861a2c734cd"},
+    {file = "pydantic_core-2.14.6-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:7e90d6cc4aad2cc1f5e16ed56e46cebf4877c62403a311af20459c15da76fd91"},
+    {file = "pydantic_core-2.14.6-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e8a5ac97ea521d7bde7621d86c30e86b798cdecd985723c4ed737a2aa9e77d0c"},
+    {file = "pydantic_core-2.14.6-cp312-none-win32.whl", hash = "sha256:f27207e8ca3e5e021e2402ba942e5b4c629718e665c81b8b306f3c8b1ddbb786"},
+    {file = "pydantic_core-2.14.6-cp312-none-win_amd64.whl", hash = "sha256:b3e5fe4538001bb82e2295b8d2a39356a84694c97cb73a566dc36328b9f83b40"},
+    {file = "pydantic_core-2.14.6-cp312-none-win_arm64.whl", hash = "sha256:64634ccf9d671c6be242a664a33c4acf12882670b09b3f163cd00a24cffbd74e"},
+    {file = "pydantic_core-2.14.6-cp37-cp37m-macosx_10_7_x86_64.whl", hash = "sha256:24368e31be2c88bd69340fbfe741b405302993242ccb476c5c3ff48aeee1afe0"},
+    {file = "pydantic_core-2.14.6-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:e33b0834f1cf779aa839975f9d8755a7c2420510c0fa1e9fa0497de77cd35d2c"},
+    {file = "pydantic_core-2.14.6-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6af4b3f52cc65f8a0bc8b1cd9676f8c21ef3e9132f21fed250f6958bd7223bed"},
+    {file = "pydantic_core-2.14.6-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d15687d7d7f40333bd8266f3814c591c2e2cd263fa2116e314f60d82086e353a"},
+    {file = "pydantic_core-2.14.6-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:095b707bb287bfd534044166ab767bec70a9bba3175dcdc3371782175c14e43c"},
+    {file = "pydantic_core-2.14.6-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:94fc0e6621e07d1e91c44e016cc0b189b48db053061cc22d6298a611de8071bb"},
+    {file = "pydantic_core-2.14.6-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1ce830e480f6774608dedfd4a90c42aac4a7af0a711f1b52f807130c2e434c06"},
+    {file = "pydantic_core-2.14.6-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:a306cdd2ad3a7d795d8e617a58c3a2ed0f76c8496fb7621b6cd514eb1532cae8"},
+    {file = "pydantic_core-2.14.6-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:2f5fa187bde8524b1e37ba894db13aadd64faa884657473b03a019f625cee9a8"},
+    {file = "pydantic_core-2.14.6-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:438027a975cc213a47c5d70672e0d29776082155cfae540c4e225716586be75e"},
+    {file = "pydantic_core-2.14.6-cp37-none-win32.whl", hash = "sha256:f96ae96a060a8072ceff4cfde89d261837b4294a4f28b84a28765470d502ccc6"},
+    {file = "pydantic_core-2.14.6-cp37-none-win_amd64.whl", hash = "sha256:e646c0e282e960345314f42f2cea5e0b5f56938c093541ea6dbf11aec2862391"},
+    {file = "pydantic_core-2.14.6-cp38-cp38-macosx_10_7_x86_64.whl", hash = "sha256:db453f2da3f59a348f514cfbfeb042393b68720787bbef2b4c6068ea362c8149"},
+    {file = "pydantic_core-2.14.6-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:3860c62057acd95cc84044e758e47b18dcd8871a328ebc8ccdefd18b0d26a21b"},
+    {file = "pydantic_core-2.14.6-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:36026d8f99c58d7044413e1b819a67ca0e0b8ebe0f25e775e6c3d1fabb3c38fb"},
+    {file = "pydantic_core-2.14.6-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8ed1af8692bd8d2a29d702f1a2e6065416d76897d726e45a1775b1444f5928a7"},
+    {file = "pydantic_core-2.14.6-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:314ccc4264ce7d854941231cf71b592e30d8d368a71e50197c905874feacc8a8"},
+    {file = "pydantic_core-2.14.6-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:982487f8931067a32e72d40ab6b47b1628a9c5d344be7f1a4e668fb462d2da42"},
+    {file = "pydantic_core-2.14.6-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2dbe357bc4ddda078f79d2a36fc1dd0494a7f2fad83a0a684465b6f24b46fe80"},
+    {file = "pydantic_core-2.14.6-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:2f6ffc6701a0eb28648c845f4945a194dc7ab3c651f535b81793251e1185ac3d"},
+    {file = "pydantic_core-2.14.6-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:7f5025db12fc6de7bc1104d826d5aee1d172f9ba6ca936bf6474c2148ac336c1"},
+    {file = "pydantic_core-2.14.6-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:dab03ed811ed1c71d700ed08bde8431cf429bbe59e423394f0f4055f1ca0ea60"},
+    {file = "pydantic_core-2.14.6-cp38-none-win32.whl", hash = "sha256:dfcbebdb3c4b6f739a91769aea5ed615023f3c88cb70df812849aef634c25fbe"},
+    {file = "pydantic_core-2.14.6-cp38-none-win_amd64.whl", hash = "sha256:99b14dbea2fdb563d8b5a57c9badfcd72083f6006caf8e126b491519c7d64ca8"},
+    {file = "pydantic_core-2.14.6-cp39-cp39-macosx_10_7_x86_64.whl", hash = "sha256:4ce8299b481bcb68e5c82002b96e411796b844d72b3e92a3fbedfe8e19813eab"},
+    {file = "pydantic_core-2.14.6-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:b9a9d92f10772d2a181b5ca339dee066ab7d1c9a34ae2421b2a52556e719756f"},
+    {file = "pydantic_core-2.14.6-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fd9e98b408384989ea4ab60206b8e100d8687da18b5c813c11e92fd8212a98e0"},
+    {file = "pydantic_core-2.14.6-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:4f86f1f318e56f5cbb282fe61eb84767aee743ebe32c7c0834690ebea50c0a6b"},
+    {file = "pydantic_core-2.14.6-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:86ce5fcfc3accf3a07a729779d0b86c5d0309a4764c897d86c11089be61da160"},
+    {file = "pydantic_core-2.14.6-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3dcf1978be02153c6a31692d4fbcc2a3f1db9da36039ead23173bc256ee3b91b"},
+    {file = "pydantic_core-2.14.6-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eedf97be7bc3dbc8addcef4142f4b4164066df0c6f36397ae4aaed3eb187d8ab"},
+    {file = "pydantic_core-2.14.6-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d5f916acf8afbcab6bacbb376ba7dc61f845367901ecd5e328fc4d4aef2fcab0"},
+    {file = "pydantic_core-2.14.6-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:8a14c192c1d724c3acbfb3f10a958c55a2638391319ce8078cb36c02283959b9"},
+    {file = "pydantic_core-2.14.6-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:0348b1dc6b76041516e8a854ff95b21c55f5a411c3297d2ca52f5528e49d8411"},
+    {file = "pydantic_core-2.14.6-cp39-none-win32.whl", hash = "sha256:de2a0645a923ba57c5527497daf8ec5df69c6eadf869e9cd46e86349146e5975"},
+    {file = "pydantic_core-2.14.6-cp39-none-win_amd64.whl", hash = "sha256:aca48506a9c20f68ee61c87f2008f81f8ee99f8d7f0104bff3c47e2d148f89d9"},
+    {file = "pydantic_core-2.14.6-pp310-pypy310_pp73-macosx_10_7_x86_64.whl", hash = "sha256:d5c28525c19f5bb1e09511669bb57353d22b94cf8b65f3a8d141c389a55dec95"},
+    {file = "pydantic_core-2.14.6-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:78d0768ee59baa3de0f4adac9e3748b4b1fffc52143caebddfd5ea2961595277"},
+    {file = "pydantic_core-2.14.6-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8b93785eadaef932e4fe9c6e12ba67beb1b3f1e5495631419c784ab87e975670"},
+    {file = "pydantic_core-2.14.6-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a874f21f87c485310944b2b2734cd6d318765bcbb7515eead33af9641816506e"},
+    {file = "pydantic_core-2.14.6-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:b89f4477d915ea43b4ceea6756f63f0288941b6443a2b28c69004fe07fde0d0d"},
+    {file = "pydantic_core-2.14.6-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:172de779e2a153d36ee690dbc49c6db568d7b33b18dc56b69a7514aecbcf380d"},
+    {file = "pydantic_core-2.14.6-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:dfcebb950aa7e667ec226a442722134539e77c575f6cfaa423f24371bb8d2e94"},
+    {file = "pydantic_core-2.14.6-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:55a23dcd98c858c0db44fc5c04fc7ed81c4b4d33c653a7c45ddaebf6563a2f66"},
+    {file = "pydantic_core-2.14.6-pp37-pypy37_pp73-macosx_10_7_x86_64.whl", hash = "sha256:4241204e4b36ab5ae466ecec5c4c16527a054c69f99bba20f6f75232a6a534e2"},
+    {file = "pydantic_core-2.14.6-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e574de99d735b3fc8364cba9912c2bec2da78775eba95cbb225ef7dda6acea24"},
+    {file = "pydantic_core-2.14.6-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1302a54f87b5cd8528e4d6d1bf2133b6aa7c6122ff8e9dc5220fbc1e07bffebd"},
+    {file = "pydantic_core-2.14.6-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:f8e81e4b55930e5ffab4a68db1af431629cf2e4066dbdbfef65348b8ab804ea8"},
+    {file = "pydantic_core-2.14.6-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:c99462ffc538717b3e60151dfaf91125f637e801f5ab008f81c402f1dff0cd0f"},
+    {file = "pydantic_core-2.14.6-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:e4cf2d5829f6963a5483ec01578ee76d329eb5caf330ecd05b3edd697e7d768a"},
+    {file = "pydantic_core-2.14.6-pp38-pypy38_pp73-macosx_10_7_x86_64.whl", hash = "sha256:cf10b7d58ae4a1f07fccbf4a0a956d705356fea05fb4c70608bb6fa81d103cda"},
+    {file = "pydantic_core-2.14.6-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:399ac0891c284fa8eb998bcfa323f2234858f5d2efca3950ae58c8f88830f145"},
+    {file = "pydantic_core-2.14.6-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9c6a5c79b28003543db3ba67d1df336f253a87d3112dac3a51b94f7d48e4c0e1"},
+    {file = "pydantic_core-2.14.6-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:599c87d79cab2a6a2a9df4aefe0455e61e7d2aeede2f8577c1b7c0aec643ee8e"},
+    {file = "pydantic_core-2.14.6-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:43e166ad47ba900f2542a80d83f9fc65fe99eb63ceec4debec160ae729824052"},
+    {file = "pydantic_core-2.14.6-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:3a0b5db001b98e1c649dd55afa928e75aa4087e587b9524a4992316fa23c9fba"},
+    {file = "pydantic_core-2.14.6-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:747265448cb57a9f37572a488a57d873fd96bf51e5bb7edb52cfb37124516da4"},
+    {file = "pydantic_core-2.14.6-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:7ebe3416785f65c28f4f9441e916bfc8a54179c8dea73c23023f7086fa601c5d"},
+    {file = "pydantic_core-2.14.6-pp39-pypy39_pp73-macosx_10_7_x86_64.whl", hash = "sha256:86c963186ca5e50d5c8287b1d1c9d3f8f024cbe343d048c5bd282aec2d8641f2"},
+    {file = "pydantic_core-2.14.6-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:e0641b506486f0b4cd1500a2a65740243e8670a2549bb02bc4556a83af84ae03"},
+    {file = "pydantic_core-2.14.6-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:71d72ca5eaaa8d38c8df16b7deb1a2da4f650c41b58bb142f3fb75d5ad4a611f"},
+    {file = "pydantic_core-2.14.6-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:27e524624eace5c59af499cd97dc18bb201dc6a7a2da24bfc66ef151c69a5f2a"},
+    {file = "pydantic_core-2.14.6-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:a3dde6cac75e0b0902778978d3b1646ca9f438654395a362cb21d9ad34b24acf"},
+    {file = "pydantic_core-2.14.6-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:00646784f6cd993b1e1c0e7b0fdcbccc375d539db95555477771c27555e3c556"},
+    {file = "pydantic_core-2.14.6-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:23598acb8ccaa3d1d875ef3b35cb6376535095e9405d91a3d57a8c7db5d29341"},
+    {file = "pydantic_core-2.14.6-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:7f41533d7e3cf9520065f610b41ac1c76bc2161415955fbcead4981b22c7611e"},
+    {file = "pydantic_core-2.14.6.tar.gz", hash = "sha256:1fd0c1d395372843fba13a51c28e3bb9d59bd7aebfeb17358ffaaa1e4dbbe948"},
+]
+
+[package.dependencies]
+typing-extensions = ">=4.6.0,<4.7.0 || >4.7.0"
+
+[[package]]
+name = "pydub"
+version = "0.25.1"
+description = "Manipulate audio with an simple and easy high level interface"
+optional = false
+python-versions = "*"
+files = [
+    {file = "pydub-0.25.1-py2.py3-none-any.whl", hash = "sha256:65617e33033874b59d87db603aa1ed450633288aefead953b30bded59cb599a6"},
+    {file = "pydub-0.25.1.tar.gz", hash = "sha256:980a33ce9949cab2a569606b65674d748ecbca4f0796887fd6f46173a7b0d30f"},
+]
+
+[[package]]
+name = "python-dotenv"
+version = "1.0.0"
+description = "Read key-value pairs from a .env file and set them as environment variables"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "python-dotenv-1.0.0.tar.gz", hash = "sha256:a8df96034aae6d2d50a4ebe8216326c61c3eb64836776504fcca410e5937a3ba"},
+    {file = "python_dotenv-1.0.0-py3-none-any.whl", hash = "sha256:f5971a9226b701070a4bf2c38c89e5a3f0d64de8debda981d1db98583009122a"},
+]
+
+[package.extras]
+cli = ["click (>=5.0)"]
+
+[[package]]
+name = "python-multipart"
+version = "0.0.6"
+description = "A streaming multipart parser for Python"
+optional = true
+python-versions = ">=3.7"
+files = [
+    {file = "python_multipart-0.0.6-py3-none-any.whl", hash = "sha256:ee698bab5ef148b0a760751c261902cd096e57e10558e11aca17646b74ee1c18"},
+    {file = "python_multipart-0.0.6.tar.gz", hash = "sha256:e9925a80bb668529f1b67c7fdb0a5dacdd7cbfc6fb0bff3ea443fe22bdd62132"},
+]
+
+[package.extras]
+dev = ["atomicwrites (==1.2.1)", "attrs (==19.2.0)", "coverage (==6.5.0)", "hatch", "invoke (==1.7.3)", "more-itertools (==4.3.0)", "pbr (==4.3.0)", "pluggy (==1.0.0)", "py (==1.11.0)", "pytest (==7.2.0)", "pytest-cov (==4.0.0)", "pytest-timeout (==2.1.0)", "pyyaml (==5.1)"]
+
+[[package]]
+name = "pywin32"
+version = "306"
+description = "Python for Window Extensions"
+optional = false
+python-versions = "*"
+files = [
+    {file = "pywin32-306-cp310-cp310-win32.whl", hash = "sha256:06d3420a5155ba65f0b72f2699b5bacf3109f36acbe8923765c22938a69dfc8d"},
+    {file = "pywin32-306-cp310-cp310-win_amd64.whl", hash = "sha256:84f4471dbca1887ea3803d8848a1616429ac94a4a8d05f4bc9c5dcfd42ca99c8"},
+    {file = "pywin32-306-cp311-cp311-win32.whl", hash = "sha256:e65028133d15b64d2ed8f06dd9fbc268352478d4f9289e69c190ecd6818b6407"},
+    {file = "pywin32-306-cp311-cp311-win_amd64.whl", hash = "sha256:a7639f51c184c0272e93f244eb24dafca9b1855707d94c192d4a0b4c01e1100e"},
+    {file = "pywin32-306-cp311-cp311-win_arm64.whl", hash = "sha256:70dba0c913d19f942a2db25217d9a1b726c278f483a919f1abfed79c9cf64d3a"},
+    {file = "pywin32-306-cp312-cp312-win32.whl", hash = "sha256:383229d515657f4e3ed1343da8be101000562bf514591ff383ae940cad65458b"},
+    {file = "pywin32-306-cp312-cp312-win_amd64.whl", hash = "sha256:37257794c1ad39ee9be652da0462dc2e394c8159dfd913a8a4e8eb6fd346da0e"},
+    {file = "pywin32-306-cp312-cp312-win_arm64.whl", hash = "sha256:5821ec52f6d321aa59e2db7e0a35b997de60c201943557d108af9d4ae1ec7040"},
+    {file = "pywin32-306-cp37-cp37m-win32.whl", hash = "sha256:1c73ea9a0d2283d889001998059f5eaaba3b6238f767c9cf2833b13e6a685f65"},
+    {file = "pywin32-306-cp37-cp37m-win_amd64.whl", hash = "sha256:72c5f621542d7bdd4fdb716227be0dd3f8565c11b280be6315b06ace35487d36"},
+    {file = "pywin32-306-cp38-cp38-win32.whl", hash = "sha256:e4c092e2589b5cf0d365849e73e02c391c1349958c5ac3e9d5ccb9a28e017b3a"},
+    {file = "pywin32-306-cp38-cp38-win_amd64.whl", hash = "sha256:e8ac1ae3601bee6ca9f7cb4b5363bf1c0badb935ef243c4733ff9a393b1690c0"},
+    {file = "pywin32-306-cp39-cp39-win32.whl", hash = "sha256:e25fd5b485b55ac9c057f67d94bc203f3f6595078d1fb3b458c9c28b7153a802"},
+    {file = "pywin32-306-cp39-cp39-win_amd64.whl", hash = "sha256:39b61c15272833b5c329a2989999dcae836b1eed650252ab1b7bfbe1d59f30f4"},
+]
+
+[[package]]
+name = "pyworld"
+version = "0.3.4"
+description = "PyWorld: a Python wrapper for WORLD vocoder"
+optional = false
+python-versions = "*"
+files = [
+    {file = "pyworld-0.3.4-cp310-cp310-win_amd64.whl", hash = "sha256:699d2478b31215893152f67bb3eef244ed77fd3b8ac6757428fbcf7f8e1a057c"},
+    {file = "pyworld-0.3.4-cp311-cp311-win_amd64.whl", hash = "sha256:61292a4dced5f4a0677aa7afdd5c601df79e70771aa63bbdd8279e6a1d0f5d7a"},
+    {file = "pyworld-0.3.4-cp36-cp36m-win32.whl", hash = "sha256:ebd9f918f54fb5dd6a16059635d904b56a5165e7e5207ab1b4fa0fb839b4efa7"},
+    {file = "pyworld-0.3.4-cp36-cp36m-win_amd64.whl", hash = "sha256:34db25abde77cc231605d0f3748742cf9535156ee239fd861241a66d43c5134c"},
+    {file = "pyworld-0.3.4-cp37-cp37m-win32.whl", hash = "sha256:8c0a4c6ef1d3ba7742b4cf773c2733743392ce525d75efda4b832abb623d8689"},
+    {file = "pyworld-0.3.4-cp37-cp37m-win_amd64.whl", hash = "sha256:235ce1c9b97986897cf60544c6d46a5eef814688b1aa0ea9d88e9877e6df015f"},
+    {file = "pyworld-0.3.4-cp38-cp38-win_amd64.whl", hash = "sha256:a1aa7ec78e4575c231bc374c825a3c5c1fefdff5c83932dcf90b7d333c156c2e"},
+    {file = "pyworld-0.3.4-cp39-cp39-win_amd64.whl", hash = "sha256:fddbbb9aec3f2341279237a907b8b625fa099086205b24aa740008becbd7e3d4"},
+    {file = "pyworld-0.3.4.tar.gz", hash = "sha256:106c70ee7a7d8c9ba488d8022f2033706929a40f0264256b8e87da5aab98303a"},
+]
+
+[package.dependencies]
+cython = ">=0.24"
+numpy = "*"
+
+[package.extras]
+sdist = ["cython (>=0.24)", "numpy"]
+test = ["nose"]
+
+[[package]]
+name = "pyyaml"
+version = "6.0.1"
+description = "YAML parser and emitter for Python"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "PyYAML-6.0.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d858aa552c999bc8a8d57426ed01e40bef403cd8ccdd0fc5f6f04a00414cac2a"},
+    {file = "PyYAML-6.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:fd66fc5d0da6d9815ba2cebeb4205f95818ff4b79c3ebe268e75d961704af52f"},
+    {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"},
+    {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"},
+    {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"},
+    {file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"},
+    {file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"},
+    {file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"},
+    {file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"},
+    {file = "PyYAML-6.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f003ed9ad21d6a4713f0a9b5a7a0a79e08dd0f221aff4525a2be4c346ee60aab"},
+    {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"},
+    {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"},
+    {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"},
+    {file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"},
+    {file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"},
+    {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
+    {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
+    {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
+    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
+    {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
+    {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
+    {file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"},
+    {file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"},
+    {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"},
+    {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"},
+    {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:afd7e57eddb1a54f0f1a974bc4391af8bcce0b444685d936840f125cf046d5bd"},
+    {file = "PyYAML-6.0.1-cp36-cp36m-win32.whl", hash = "sha256:fca0e3a251908a499833aa292323f32437106001d436eca0e6e7833256674585"},
+    {file = "PyYAML-6.0.1-cp36-cp36m-win_amd64.whl", hash = "sha256:f22ac1c3cac4dbc50079e965eba2c1058622631e526bd9afd45fedd49ba781fa"},
+    {file = "PyYAML-6.0.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:b1275ad35a5d18c62a7220633c913e1b42d44b46ee12554e5fd39c70a243d6a3"},
+    {file = "PyYAML-6.0.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:18aeb1bf9a78867dc38b259769503436b7c72f7a1f1f4c93ff9a17de54319b27"},
+    {file = "PyYAML-6.0.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:596106435fa6ad000c2991a98fa58eeb8656ef2325d7e158344fb33864ed87e3"},
+    {file = "PyYAML-6.0.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:baa90d3f661d43131ca170712d903e6295d1f7a0f595074f151c0aed377c9b9c"},
+    {file = "PyYAML-6.0.1-cp37-cp37m-win32.whl", hash = "sha256:9046c58c4395dff28dd494285c82ba00b546adfc7ef001486fbf0324bc174fba"},
+    {file = "PyYAML-6.0.1-cp37-cp37m-win_amd64.whl", hash = "sha256:4fb147e7a67ef577a588a0e2c17b6db51dda102c71de36f8549b6816a96e1867"},
+    {file = "PyYAML-6.0.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1d4c7e777c441b20e32f52bd377e0c409713e8bb1386e1099c2415f26e479595"},
+    {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"},
+    {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"},
+    {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"},
+    {file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"},
+    {file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"},
+    {file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"},
+    {file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"},
+    {file = "PyYAML-6.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:c8098ddcc2a85b61647b2590f825f3db38891662cfc2fc776415143f599bb859"},
+    {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"},
+    {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"},
+    {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"},
+    {file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"},
+    {file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"},
+    {file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"},
+    {file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"},
+]
+
+[[package]]
+name = "regex"
+version = "2023.12.25"
+description = "Alternative regular expression module, to replace re."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "regex-2023.12.25-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:0694219a1d54336fd0445ea382d49d36882415c0134ee1e8332afd1529f0baa5"},
+    {file = "regex-2023.12.25-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:b014333bd0217ad3d54c143de9d4b9a3ca1c5a29a6d0d554952ea071cff0f1f8"},
+    {file = "regex-2023.12.25-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d865984b3f71f6d0af64d0d88f5733521698f6c16f445bb09ce746c92c97c586"},
+    {file = "regex-2023.12.25-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1e0eabac536b4cc7f57a5f3d095bfa557860ab912f25965e08fe1545e2ed8b4c"},
+    {file = "regex-2023.12.25-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c25a8ad70e716f96e13a637802813f65d8a6760ef48672aa3502f4c24ea8b400"},
+    {file = "regex-2023.12.25-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a9b6d73353f777630626f403b0652055ebfe8ff142a44ec2cf18ae470395766e"},
+    {file = "regex-2023.12.25-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a9cc99d6946d750eb75827cb53c4371b8b0fe89c733a94b1573c9dd16ea6c9e4"},
+    {file = "regex-2023.12.25-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:88d1f7bef20c721359d8675f7d9f8e414ec5003d8f642fdfd8087777ff7f94b5"},
+    {file = "regex-2023.12.25-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:cb3fe77aec8f1995611f966d0c656fdce398317f850d0e6e7aebdfe61f40e1cd"},
+    {file = "regex-2023.12.25-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:7aa47c2e9ea33a4a2a05f40fcd3ea36d73853a2aae7b4feab6fc85f8bf2c9704"},
+    {file = "regex-2023.12.25-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:df26481f0c7a3f8739fecb3e81bc9da3fcfae34d6c094563b9d4670b047312e1"},
+    {file = "regex-2023.12.25-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:c40281f7d70baf6e0db0c2f7472b31609f5bc2748fe7275ea65a0b4601d9b392"},
+    {file = "regex-2023.12.25-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:d94a1db462d5690ebf6ae86d11c5e420042b9898af5dcf278bd97d6bda065423"},
+    {file = "regex-2023.12.25-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:ba1b30765a55acf15dce3f364e4928b80858fa8f979ad41f862358939bdd1f2f"},
+    {file = "regex-2023.12.25-cp310-cp310-win32.whl", hash = "sha256:150c39f5b964e4d7dba46a7962a088fbc91f06e606f023ce57bb347a3b2d4630"},
+    {file = "regex-2023.12.25-cp310-cp310-win_amd64.whl", hash = "sha256:09da66917262d9481c719599116c7dc0c321ffcec4b1f510c4f8a066f8768105"},
+    {file = "regex-2023.12.25-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:1b9d811f72210fa9306aeb88385b8f8bcef0dfbf3873410413c00aa94c56c2b6"},
+    {file = "regex-2023.12.25-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d902a43085a308cef32c0d3aea962524b725403fd9373dea18110904003bac97"},
+    {file = "regex-2023.12.25-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d166eafc19f4718df38887b2bbe1467a4f74a9830e8605089ea7a30dd4da8887"},
+    {file = "regex-2023.12.25-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c7ad32824b7f02bb3c9f80306d405a1d9b7bb89362d68b3c5a9be53836caebdb"},
+    {file = "regex-2023.12.25-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:636ba0a77de609d6510235b7f0e77ec494d2657108f777e8765efc060094c98c"},
+    {file = "regex-2023.12.25-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0fda75704357805eb953a3ee15a2b240694a9a514548cd49b3c5124b4e2ad01b"},
+    {file = "regex-2023.12.25-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f72cbae7f6b01591f90814250e636065850c5926751af02bb48da94dfced7baa"},
+    {file = "regex-2023.12.25-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:db2a0b1857f18b11e3b0e54ddfefc96af46b0896fb678c85f63fb8c37518b3e7"},
+    {file = "regex-2023.12.25-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:7502534e55c7c36c0978c91ba6f61703faf7ce733715ca48f499d3dbbd7657e0"},
+    {file = "regex-2023.12.25-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:e8c7e08bb566de4faaf11984af13f6bcf6a08f327b13631d41d62592681d24fe"},
+    {file = "regex-2023.12.25-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:283fc8eed679758de38fe493b7d7d84a198b558942b03f017b1f94dda8efae80"},
+    {file = "regex-2023.12.25-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:f44dd4d68697559d007462b0a3a1d9acd61d97072b71f6d1968daef26bc744bd"},
+    {file = "regex-2023.12.25-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:67d3ccfc590e5e7197750fcb3a2915b416a53e2de847a728cfa60141054123d4"},
+    {file = "regex-2023.12.25-cp311-cp311-win32.whl", hash = "sha256:68191f80a9bad283432385961d9efe09d783bcd36ed35a60fb1ff3f1ec2efe87"},
+    {file = "regex-2023.12.25-cp311-cp311-win_amd64.whl", hash = "sha256:7d2af3f6b8419661a0c421584cfe8aaec1c0e435ce7e47ee2a97e344b98f794f"},
+    {file = "regex-2023.12.25-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:8a0ccf52bb37d1a700375a6b395bff5dd15c50acb745f7db30415bae3c2b0715"},
+    {file = "regex-2023.12.25-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:c3c4a78615b7762740531c27cf46e2f388d8d727d0c0c739e72048beb26c8a9d"},
+    {file = "regex-2023.12.25-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ad83e7545b4ab69216cef4cc47e344d19622e28aabec61574b20257c65466d6a"},
+    {file = "regex-2023.12.25-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b7a635871143661feccce3979e1727c4e094f2bdfd3ec4b90dfd4f16f571a87a"},
+    {file = "regex-2023.12.25-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d498eea3f581fbe1b34b59c697512a8baef88212f92e4c7830fcc1499f5b45a5"},
+    {file = "regex-2023.12.25-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:43f7cd5754d02a56ae4ebb91b33461dc67be8e3e0153f593c509e21d219c5060"},
+    {file = "regex-2023.12.25-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:51f4b32f793812714fd5307222a7f77e739b9bc566dc94a18126aba3b92b98a3"},
+    {file = "regex-2023.12.25-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ba99d8077424501b9616b43a2d208095746fb1284fc5ba490139651f971d39d9"},
+    {file = "regex-2023.12.25-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:4bfc2b16e3ba8850e0e262467275dd4d62f0d045e0e9eda2bc65078c0110a11f"},
+    {file = "regex-2023.12.25-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:8c2c19dae8a3eb0ea45a8448356ed561be843b13cbc34b840922ddf565498c1c"},
+    {file = "regex-2023.12.25-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:60080bb3d8617d96f0fb7e19796384cc2467447ef1c491694850ebd3670bc457"},
+    {file = "regex-2023.12.25-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:b77e27b79448e34c2c51c09836033056a0547aa360c45eeeb67803da7b0eedaf"},
+    {file = "regex-2023.12.25-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:518440c991f514331f4850a63560321f833979d145d7d81186dbe2f19e27ae3d"},
+    {file = "regex-2023.12.25-cp312-cp312-win32.whl", hash = "sha256:e2610e9406d3b0073636a3a2e80db05a02f0c3169b5632022b4e81c0364bcda5"},
+    {file = "regex-2023.12.25-cp312-cp312-win_amd64.whl", hash = "sha256:cc37b9aeebab425f11f27e5e9e6cf580be7206c6582a64467a14dda211abc232"},
+    {file = "regex-2023.12.25-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:da695d75ac97cb1cd725adac136d25ca687da4536154cdc2815f576e4da11c69"},
+    {file = "regex-2023.12.25-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d126361607b33c4eb7b36debc173bf25d7805847346dd4d99b5499e1fef52bc7"},
+    {file = "regex-2023.12.25-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4719bb05094d7d8563a450cf8738d2e1061420f79cfcc1fa7f0a44744c4d8f73"},
+    {file = "regex-2023.12.25-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5dd58946bce44b53b06d94aa95560d0b243eb2fe64227cba50017a8d8b3cd3e2"},
+    {file = "regex-2023.12.25-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:22a86d9fff2009302c440b9d799ef2fe322416d2d58fc124b926aa89365ec482"},
+    {file = "regex-2023.12.25-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2aae8101919e8aa05ecfe6322b278f41ce2994c4a430303c4cd163fef746e04f"},
+    {file = "regex-2023.12.25-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:e692296c4cc2873967771345a876bcfc1c547e8dd695c6b89342488b0ea55cd8"},
+    {file = "regex-2023.12.25-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:263ef5cc10979837f243950637fffb06e8daed7f1ac1e39d5910fd29929e489a"},
+    {file = "regex-2023.12.25-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:d6f7e255e5fa94642a0724e35406e6cb7001c09d476ab5fce002f652b36d0c39"},
+    {file = "regex-2023.12.25-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:88ad44e220e22b63b0f8f81f007e8abbb92874d8ced66f32571ef8beb0643b2b"},
+    {file = "regex-2023.12.25-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:3a17d3ede18f9cedcbe23d2daa8a2cd6f59fe2bf082c567e43083bba3fb00347"},
+    {file = "regex-2023.12.25-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:d15b274f9e15b1a0b7a45d2ac86d1f634d983ca40d6b886721626c47a400bf39"},
+    {file = "regex-2023.12.25-cp37-cp37m-win32.whl", hash = "sha256:ed19b3a05ae0c97dd8f75a5d8f21f7723a8c33bbc555da6bbe1f96c470139d3c"},
+    {file = "regex-2023.12.25-cp37-cp37m-win_amd64.whl", hash = "sha256:a6d1047952c0b8104a1d371f88f4ab62e6275567d4458c1e26e9627ad489b445"},
+    {file = "regex-2023.12.25-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:b43523d7bc2abd757119dbfb38af91b5735eea45537ec6ec3a5ec3f9562a1c53"},
+    {file = "regex-2023.12.25-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:efb2d82f33b2212898f1659fb1c2e9ac30493ac41e4d53123da374c3b5541e64"},
+    {file = "regex-2023.12.25-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:b7fca9205b59c1a3d5031f7e64ed627a1074730a51c2a80e97653e3e9fa0d415"},
+    {file = "regex-2023.12.25-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:086dd15e9435b393ae06f96ab69ab2d333f5d65cbe65ca5a3ef0ec9564dfe770"},
+    {file = "regex-2023.12.25-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e81469f7d01efed9b53740aedd26085f20d49da65f9c1f41e822a33992cb1590"},
+    {file = "regex-2023.12.25-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:34e4af5b27232f68042aa40a91c3b9bb4da0eeb31b7632e0091afc4310afe6cb"},
+    {file = "regex-2023.12.25-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9852b76ab558e45b20bf1893b59af64a28bd3820b0c2efc80e0a70a4a3ea51c1"},
+    {file = "regex-2023.12.25-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ff100b203092af77d1a5a7abe085b3506b7eaaf9abf65b73b7d6905b6cb76988"},
+    {file = "regex-2023.12.25-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:cc038b2d8b1470364b1888a98fd22d616fba2b6309c5b5f181ad4483e0017861"},
+    {file = "regex-2023.12.25-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:094ba386bb5c01e54e14434d4caabf6583334090865b23ef58e0424a6286d3dc"},
+    {file = "regex-2023.12.25-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:5cd05d0f57846d8ba4b71d9c00f6f37d6b97d5e5ef8b3c3840426a475c8f70f4"},
+    {file = "regex-2023.12.25-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:9aa1a67bbf0f957bbe096375887b2505f5d8ae16bf04488e8b0f334c36e31360"},
+    {file = "regex-2023.12.25-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:98a2636994f943b871786c9e82bfe7883ecdaba2ef5df54e1450fa9869d1f756"},
+    {file = "regex-2023.12.25-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:37f8e93a81fc5e5bd8db7e10e62dc64261bcd88f8d7e6640aaebe9bc180d9ce2"},
+    {file = "regex-2023.12.25-cp38-cp38-win32.whl", hash = "sha256:d78bd484930c1da2b9679290a41cdb25cc127d783768a0369d6b449e72f88beb"},
+    {file = "regex-2023.12.25-cp38-cp38-win_amd64.whl", hash = "sha256:b521dcecebc5b978b447f0f69b5b7f3840eac454862270406a39837ffae4e697"},
+    {file = "regex-2023.12.25-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:f7bc09bc9c29ebead055bcba136a67378f03d66bf359e87d0f7c759d6d4ffa31"},
+    {file = "regex-2023.12.25-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:e14b73607d6231f3cc4622809c196b540a6a44e903bcfad940779c80dffa7be7"},
+    {file = "regex-2023.12.25-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:9eda5f7a50141291beda3edd00abc2d4a5b16c29c92daf8d5bd76934150f3edc"},
+    {file = "regex-2023.12.25-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cc6bb9aa69aacf0f6032c307da718f61a40cf970849e471254e0e91c56ffca95"},
+    {file = "regex-2023.12.25-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:298dc6354d414bc921581be85695d18912bea163a8b23cac9a2562bbcd5088b1"},
+    {file = "regex-2023.12.25-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2f4e475a80ecbd15896a976aa0b386c5525d0ed34d5c600b6d3ebac0a67c7ddf"},
+    {file = "regex-2023.12.25-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:531ac6cf22b53e0696f8e1d56ce2396311254eb806111ddd3922c9d937151dae"},
+    {file = "regex-2023.12.25-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:22f3470f7524b6da61e2020672df2f3063676aff444db1daa283c2ea4ed259d6"},
+    {file = "regex-2023.12.25-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:89723d2112697feaa320c9d351e5f5e7b841e83f8b143dba8e2d2b5f04e10923"},
+    {file = "regex-2023.12.25-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:0ecf44ddf9171cd7566ef1768047f6e66975788258b1c6c6ca78098b95cf9a3d"},
+    {file = "regex-2023.12.25-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:905466ad1702ed4acfd67a902af50b8db1feeb9781436372261808df7a2a7bca"},
+    {file = "regex-2023.12.25-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:4558410b7a5607a645e9804a3e9dd509af12fb72b9825b13791a37cd417d73a5"},
+    {file = "regex-2023.12.25-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:7e316026cc1095f2a3e8cc012822c99f413b702eaa2ca5408a513609488cb62f"},
+    {file = "regex-2023.12.25-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:3b1de218d5375cd6ac4b5493e0b9f3df2be331e86520f23382f216c137913d20"},
+    {file = "regex-2023.12.25-cp39-cp39-win32.whl", hash = "sha256:11a963f8e25ab5c61348d090bf1b07f1953929c13bd2309a0662e9ff680763c9"},
+    {file = "regex-2023.12.25-cp39-cp39-win_amd64.whl", hash = "sha256:e693e233ac92ba83a87024e1d32b5f9ab15ca55ddd916d878146f4e3406b5c91"},
+    {file = "regex-2023.12.25.tar.gz", hash = "sha256:29171aa128da69afdf4bde412d5bedc335f2ca8fcfe4489038577d05f16181e5"},
+]
+
+[[package]]
+name = "requests"
+version = "2.31.0"
+description = "Python HTTP for Humans."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "requests-2.31.0-py3-none-any.whl", hash = "sha256:58cd2187c01e70e6e26505bca751777aa9f2ee0b7f4300988b709f44e013003f"},
+    {file = "requests-2.31.0.tar.gz", hash = "sha256:942c5a758f98d790eaed1a29cb6eefc7ffb0d1cf7af05c3d2791656dbd6ad1e1"},
+]
+
+[package.dependencies]
+certifi = ">=2017.4.17"
+charset-normalizer = ">=2,<4"
+idna = ">=2.5,<4"
+urllib3 = ">=1.21.1,<3"
+
+[package.extras]
+socks = ["PySocks (>=1.5.6,!=1.5.7)"]
+use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
+
+[[package]]
+name = "resampy"
+version = "0.4.2"
+description = "Efficient signal resampling"
+optional = false
+python-versions = "*"
+files = [
+    {file = "resampy-0.4.2-py3-none-any.whl", hash = "sha256:4340b6c4e685a865621dfcf016e2a3dd49d865446b6025e30fe88567f22e052e"},
+    {file = "resampy-0.4.2.tar.gz", hash = "sha256:0a469e6ddb89956f4fd6c88728300e4bbd186fae569dd4fd17dae51a91cbaa15"},
+]
+
+[package.dependencies]
+numba = ">=0.53"
+numpy = ">=1.17"
+
+[package.extras]
+design = ["optuna (>=2.10.0)"]
+docs = ["numpydoc", "sphinx (!=1.3.1)"]
+tests = ["pytest (<8)", "pytest-cov", "scipy (>=1.0)"]
+
+[[package]]
+name = "sacrebleu"
+version = "2.4.0"
+description = "Hassle-free computation of shareable, comparable, and reproducible BLEU, chrF, and TER scores"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "sacrebleu-2.4.0-py3-none-any.whl", hash = "sha256:fc7c34464a56d691bf5e37c4b5292142d2273b02516ac61e264cd19035fff981"},
+    {file = "sacrebleu-2.4.0.tar.gz", hash = "sha256:d9e918147dc0777b2e159bff3246b8eb22d76f3b4ee3e6c6cbda05dc25dbb9c0"},
+]
+
+[package.dependencies]
+colorama = "*"
+lxml = "*"
+numpy = ">=1.17"
+portalocker = "*"
+regex = "*"
+tabulate = ">=0.8.9"
+
+[package.extras]
+ja = ["ipadic (>=1.0,<2.0)", "mecab-python3 (>=1.0.5,<=1.0.6)"]
+ko = ["mecab-ko (>=1.0.0,<=1.0.1)", "mecab-ko-dic (>=1.0,<2.0)"]
+
+[[package]]
+name = "scikit-learn"
+version = "1.4.0"
+description = "A set of python modules for machine learning and data mining"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "scikit-learn-1.4.0.tar.gz", hash = "sha256:d4373c984eba20e393216edd51a3e3eede56cbe93d4247516d205643c3b93121"},
+    {file = "scikit_learn-1.4.0-1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:fce93a7473e2f4ee4cc280210968288d6a7d7ad8dc6fa7bb7892145e407085f9"},
+    {file = "scikit_learn-1.4.0-1-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:d77df3d1e15fc37a9329999979fa7868ba8655dbab21fe97fc7ddabac9e08cc7"},
+    {file = "scikit_learn-1.4.0-1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2404659fedec40eeafa310cd14d613e564d13dbf8f3c752d31c095195ec05de6"},
+    {file = "scikit_learn-1.4.0-1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e98632da8f6410e6fb6bf66937712c949b4010600ccd3f22a5388a83e610cc3c"},
+    {file = "scikit_learn-1.4.0-1-cp310-cp310-win_amd64.whl", hash = "sha256:11b3b140f70fbc9f6a08884631ae8dd60a4bb2d7d6d1de92738ea42b740d8992"},
+    {file = "scikit_learn-1.4.0-1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a8341eabdc754d5ab91641a7763243845e96b6d68e03e472531e88a4f1b09f21"},
+    {file = "scikit_learn-1.4.0-1-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:d1f6bce875ac2bb6b52514f67c185c564ccd299a05b65b7bab091a4c13dde12d"},
+    {file = "scikit_learn-1.4.0-1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c408b46b2fd61952d519ea1af2f8f0a7a703e1433923ab1704c4131520b2083b"},
+    {file = "scikit_learn-1.4.0-1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2b465dd1dcd237b7b1dcd1a9048ccbf70a98c659474324fa708464c3a2533fad"},
+    {file = "scikit_learn-1.4.0-1-cp311-cp311-win_amd64.whl", hash = "sha256:0db8e22c42f7980fe5eb22069b1f84c48966f3e0d23a01afde5999e3987a2501"},
+    {file = "scikit_learn-1.4.0-1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:e7eef6ea2ed289af40e88c0be9f7704ca8b5de18508a06897c3fe21e0905efdf"},
+    {file = "scikit_learn-1.4.0-1-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:349669b01435bc4dbf25c6410b0892073befdaec52637d1a1d1ff53865dc8db3"},
+    {file = "scikit_learn-1.4.0-1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d439c584e58434d0350701bd33f6c10b309e851fccaf41c121aed55f6851d8cf"},
+    {file = "scikit_learn-1.4.0-1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a0e2427d9ef46477625ab9b55c1882844fe6fc500f418c3f8e650200182457bc"},
+    {file = "scikit_learn-1.4.0-1-cp312-cp312-win_amd64.whl", hash = "sha256:d3d75343940e7bf9b85c830c93d34039fa015eeb341c5c0b4cd7a90dadfe00d4"},
+    {file = "scikit_learn-1.4.0-1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:76986d22e884ab062b1beecdd92379656e9d3789ecc1f9870923c178de55f9fe"},
+    {file = "scikit_learn-1.4.0-1-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:e22446ad89f1cb7657f0d849dcdc345b48e2d10afa3daf2925fdb740f85b714c"},
+    {file = "scikit_learn-1.4.0-1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:74812c9eabb265be69d738a8ea8d4884917a59637fcbf88a5f0e9020498bc6b3"},
+    {file = "scikit_learn-1.4.0-1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aad2a63e0dd386b92da3270887a29b308af4d7c750d8c4995dfd9a4798691bcc"},
+    {file = "scikit_learn-1.4.0-1-cp39-cp39-win_amd64.whl", hash = "sha256:53b9e29177897c37e2ff9d4ba6ca12fdb156e22523e463db05def303f5c72b5c"},
+    {file = "scikit_learn-1.4.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:cb8f044a8f5962613ce1feb4351d66f8d784bd072d36393582f351859b065f7d"},
+    {file = "scikit_learn-1.4.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:a6372c90bbf302387792108379f1ec77719c1618d88496d0df30cb8e370b4661"},
+    {file = "scikit_learn-1.4.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:785ce3c352bf697adfda357c3922c94517a9376002971bc5ea50896144bc8916"},
+    {file = "scikit_learn-1.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0aba2a20d89936d6e72d95d05e3bf1db55bca5c5920926ad7b92c34f5e7d3bbe"},
+    {file = "scikit_learn-1.4.0-cp310-cp310-win_amd64.whl", hash = "sha256:2bac5d56b992f8f06816f2cd321eb86071c6f6d44bb4b1cb3d626525820d754b"},
+    {file = "scikit_learn-1.4.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:27ae4b0f1b2c77107c096a7e05b33458354107b47775428d1f11b23e30a73e8a"},
+    {file = "scikit_learn-1.4.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:5c5c62ffb52c3ffb755eb21fa74cc2cbf2c521bd53f5c04eaa10011dbecf5f80"},
+    {file = "scikit_learn-1.4.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7f0d2018ac6fa055dab65fe8a485967990d33c672d55bc254c56c35287b02fab"},
+    {file = "scikit_learn-1.4.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:91a8918c415c4b4bf1d60c38d32958849a9191c2428ab35d30b78354085c7c7a"},
+    {file = "scikit_learn-1.4.0-cp311-cp311-win_amd64.whl", hash = "sha256:80a21de63275f8bcd7877b3e781679d2ff1eddfed515a599f95b2502a3283d42"},
+    {file = "scikit_learn-1.4.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:0f33bbafb310c26b81c4d41ecaebdbc1f63498a3f13461d50ed9a2e8f24d28e4"},
+    {file = "scikit_learn-1.4.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:8b6ac1442ec714b4911e5aef8afd82c691b5c88b525ea58299d455acc4e8dcec"},
+    {file = "scikit_learn-1.4.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:05fc5915b716c6cc60a438c250108e9a9445b522975ed37e416d5ea4f9a63381"},
+    {file = "scikit_learn-1.4.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:842b7d6989f3c574685e18da6f91223eb32301d0f93903dd399894250835a6f7"},
+    {file = "scikit_learn-1.4.0-cp312-cp312-win_amd64.whl", hash = "sha256:88bcb586fdff865372df1bc6be88bb7e6f9e0aa080dab9f54f5cac7eca8e2b6b"},
+    {file = "scikit_learn-1.4.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:f77674647dd31f56cb12ed13ed25b6ed43a056fffef051715022d2ebffd7a7d1"},
+    {file = "scikit_learn-1.4.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:833999872e2920ce00f3a50839946bdac7539454e200eb6db54898a41f4bfd43"},
+    {file = "scikit_learn-1.4.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:970ec697accaef10fb4f51763f3a7b1250f9f0553cf05514d0e94905322a0172"},
+    {file = "scikit_learn-1.4.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:923d778f378ebacca2c672ab1740e5a413e437fb45ab45ab02578f8b689e5d43"},
+    {file = "scikit_learn-1.4.0-cp39-cp39-win_amd64.whl", hash = "sha256:1d041bc95006b545b59e458399e3175ab11ca7a03dc9a74a573ac891f5df1489"},
+]
+
+[package.dependencies]
+joblib = ">=1.2.0"
+numpy = ">=1.19.5"
+scipy = ">=1.6.0"
+threadpoolctl = ">=2.0.0"
+
+[package.extras]
+benchmark = ["matplotlib (>=3.3.4)", "memory-profiler (>=0.57.0)", "pandas (>=1.1.5)"]
+docs = ["Pillow (>=7.1.2)", "matplotlib (>=3.3.4)", "memory-profiler (>=0.57.0)", "numpydoc (>=1.2.0)", "pandas (>=1.1.5)", "plotly (>=5.14.0)", "pooch (>=1.6.0)", "scikit-image (>=0.17.2)", "seaborn (>=0.9.0)", "sphinx (>=6.0.0)", "sphinx-copybutton (>=0.5.2)", "sphinx-gallery (>=0.15.0)", "sphinx-prompt (>=1.3.0)", "sphinxext-opengraph (>=0.4.2)"]
+examples = ["matplotlib (>=3.3.4)", "pandas (>=1.1.5)", "plotly (>=5.14.0)", "pooch (>=1.6.0)", "scikit-image (>=0.17.2)", "seaborn (>=0.9.0)"]
+tests = ["black (>=23.3.0)", "matplotlib (>=3.3.4)", "mypy (>=1.3)", "numpydoc (>=1.2.0)", "pandas (>=1.1.5)", "polars (>=0.19.12)", "pooch (>=1.6.0)", "pyamg (>=4.0.0)", "pyarrow (>=12.0.0)", "pytest (>=7.1.2)", "pytest-cov (>=2.9.0)", "ruff (>=0.0.272)", "scikit-image (>=0.17.2)"]
+
+[[package]]
+name = "scipy"
+version = "1.12.0"
+description = "Fundamental algorithms for scientific computing in Python"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "scipy-1.12.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:78e4402e140879387187f7f25d91cc592b3501a2e51dfb320f48dfb73565f10b"},
+    {file = "scipy-1.12.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:f5f00ebaf8de24d14b8449981a2842d404152774c1a1d880c901bf454cb8e2a1"},
+    {file = "scipy-1.12.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e53958531a7c695ff66c2e7bb7b79560ffdc562e2051644c5576c39ff8efb563"},
+    {file = "scipy-1.12.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5e32847e08da8d895ce09d108a494d9eb78974cf6de23063f93306a3e419960c"},
+    {file = "scipy-1.12.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:4c1020cad92772bf44b8e4cdabc1df5d87376cb219742549ef69fc9fd86282dd"},
+    {file = "scipy-1.12.0-cp310-cp310-win_amd64.whl", hash = "sha256:75ea2a144096b5e39402e2ff53a36fecfd3b960d786b7efd3c180e29c39e53f2"},
+    {file = "scipy-1.12.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:408c68423f9de16cb9e602528be4ce0d6312b05001f3de61fe9ec8b1263cad08"},
+    {file = "scipy-1.12.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:5adfad5dbf0163397beb4aca679187d24aec085343755fcdbdeb32b3679f254c"},
+    {file = "scipy-1.12.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c3003652496f6e7c387b1cf63f4bb720951cfa18907e998ea551e6de51a04467"},
+    {file = "scipy-1.12.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b8066bce124ee5531d12a74b617d9ac0ea59245246410e19bca549656d9a40a"},
+    {file = "scipy-1.12.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:8bee4993817e204d761dba10dbab0774ba5a8612e57e81319ea04d84945375ba"},
+    {file = "scipy-1.12.0-cp311-cp311-win_amd64.whl", hash = "sha256:a24024d45ce9a675c1fb8494e8e5244efea1c7a09c60beb1eeb80373d0fecc70"},
+    {file = "scipy-1.12.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:e7e76cc48638228212c747ada851ef355c2bb5e7f939e10952bc504c11f4e372"},
+    {file = "scipy-1.12.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:f7ce148dffcd64ade37b2df9315541f9adad6efcaa86866ee7dd5db0c8f041c3"},
+    {file = "scipy-1.12.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9c39f92041f490422924dfdb782527a4abddf4707616e07b021de33467f917bc"},
+    {file = "scipy-1.12.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a7ebda398f86e56178c2fa94cad15bf457a218a54a35c2a7b4490b9f9cb2676c"},
+    {file = "scipy-1.12.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:95e5c750d55cf518c398a8240571b0e0782c2d5a703250872f36eaf737751338"},
+    {file = "scipy-1.12.0-cp312-cp312-win_amd64.whl", hash = "sha256:e646d8571804a304e1da01040d21577685ce8e2db08ac58e543eaca063453e1c"},
+    {file = "scipy-1.12.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:913d6e7956c3a671de3b05ccb66b11bc293f56bfdef040583a7221d9e22a2e35"},
+    {file = "scipy-1.12.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:bba1b0c7256ad75401c73e4b3cf09d1f176e9bd4248f0d3112170fb2ec4db067"},
+    {file = "scipy-1.12.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:730badef9b827b368f351eacae2e82da414e13cf8bd5051b4bdfd720271a5371"},
+    {file = "scipy-1.12.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6546dc2c11a9df6926afcbdd8a3edec28566e4e785b915e849348c6dd9f3f490"},
+    {file = "scipy-1.12.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:196ebad3a4882081f62a5bf4aeb7326aa34b110e533aab23e4374fcccb0890dc"},
+    {file = "scipy-1.12.0-cp39-cp39-win_amd64.whl", hash = "sha256:b360f1b6b2f742781299514e99ff560d1fe9bd1bff2712894b52abe528d1fd1e"},
+    {file = "scipy-1.12.0.tar.gz", hash = "sha256:4bf5abab8a36d20193c698b0f1fc282c1d083c94723902c447e5d2f1780936a3"},
+]
+
+[package.dependencies]
+numpy = ">=1.22.4,<1.29.0"
+
+[package.extras]
+dev = ["click", "cython-lint (>=0.12.2)", "doit (>=0.36.0)", "mypy", "pycodestyle", "pydevtool", "rich-click", "ruff", "types-psutil", "typing_extensions"]
+doc = ["jupytext", "matplotlib (>2)", "myst-nb", "numpydoc", "pooch", "pydata-sphinx-theme (==0.9.0)", "sphinx (!=4.1.0)", "sphinx-design (>=0.2.0)"]
+test = ["asv", "gmpy2", "hypothesis", "mpmath", "pooch", "pytest", "pytest-cov", "pytest-timeout", "pytest-xdist", "scikit-umfpack", "threadpoolctl"]
+
+[[package]]
+name = "sniffio"
+version = "1.3.0"
+description = "Sniff out which async library your code is running under"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "sniffio-1.3.0-py3-none-any.whl", hash = "sha256:eecefdce1e5bbfb7ad2eeaabf7c1eeb404d7757c379bd1f7e5cce9d8bf425384"},
+    {file = "sniffio-1.3.0.tar.gz", hash = "sha256:e60305c5e5d314f5389259b7f22aaa33d8f7dee49763119234af3755c55b9101"},
+]
+
+[[package]]
+name = "soundfile"
+version = "0.12.1"
+description = "An audio library based on libsndfile, CFFI and NumPy"
+optional = false
+python-versions = "*"
+files = [
+    {file = "soundfile-0.12.1-py2.py3-none-any.whl", hash = "sha256:828a79c2e75abab5359f780c81dccd4953c45a2c4cd4f05ba3e233ddf984b882"},
+    {file = "soundfile-0.12.1-py2.py3-none-macosx_10_9_x86_64.whl", hash = "sha256:d922be1563ce17a69582a352a86f28ed8c9f6a8bc951df63476ffc310c064bfa"},
+    {file = "soundfile-0.12.1-py2.py3-none-macosx_11_0_arm64.whl", hash = "sha256:bceaab5c4febb11ea0554566784bcf4bc2e3977b53946dda2b12804b4fe524a8"},
+    {file = "soundfile-0.12.1-py2.py3-none-manylinux_2_17_x86_64.whl", hash = "sha256:2dc3685bed7187c072a46ab4ffddd38cef7de9ae5eb05c03df2ad569cf4dacbc"},
+    {file = "soundfile-0.12.1-py2.py3-none-manylinux_2_31_x86_64.whl", hash = "sha256:074247b771a181859d2bc1f98b5ebf6d5153d2c397b86ee9e29ba602a8dfe2a6"},
+    {file = "soundfile-0.12.1-py2.py3-none-win32.whl", hash = "sha256:59dfd88c79b48f441bbf6994142a19ab1de3b9bb7c12863402c2bc621e49091a"},
+    {file = "soundfile-0.12.1-py2.py3-none-win_amd64.whl", hash = "sha256:0d86924c00b62552b650ddd28af426e3ff2d4dc2e9047dae5b3d8452e0a49a77"},
+    {file = "soundfile-0.12.1.tar.gz", hash = "sha256:e8e1017b2cf1dda767aef19d2fd9ee5ebe07e050d430f77a0a7c66ba08b8cdae"},
+]
+
+[package.dependencies]
+cffi = ">=1.0"
+
+[package.extras]
+numpy = ["numpy"]
+
+[[package]]
+name = "soxr"
+version = "0.3.7"
+description = "High quality, one-dimensional sample-rate conversion library"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "soxr-0.3.7-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ac81c4af6a993d5b7c0b466bbac4835bad2b14ec32f342b2c1f83e4cf825e301"},
+    {file = "soxr-0.3.7-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8d8a2b3e7f8d0255e2484fb82cb66c86da6fb25b342ef793cceca9ce9a61aa16"},
+    {file = "soxr-0.3.7-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd6eb6f6bbda2e8de36672cf2f0529ced6e638773150744ef075be0cc4f52c"},
+    {file = "soxr-0.3.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e47d86af35b942c92606fc2d5dfccf3f01309329475571ae2312bbf9edc3a790"},
+    {file = "soxr-0.3.7-cp310-cp310-win_amd64.whl", hash = "sha256:0e291adfaf9f2a7c4dd180a1b8c280f9beb1c84cb381853e4f4b3434d002ed7f"},
+    {file = "soxr-0.3.7-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:9e811450f0e91972932bd37ac58e32e44002c2c99db2aa926a9e7ba164545034"},
+    {file = "soxr-0.3.7-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:9cea63014ce91035074e1228c9340e2b8609faf964e268705fcac5135d05060c"},
+    {file = "soxr-0.3.7-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bfab27830f6217a15b83445988225c3aeea3bbccfa9399ced291e53e1b05925d"},
+    {file = "soxr-0.3.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:286858e3078d76c11b6d490b66fed3c9bb2a4229759f6be03ceef5c02189bf2c"},
+    {file = "soxr-0.3.7-cp311-cp311-win_amd64.whl", hash = "sha256:54985ff33292192d2937be80df3e5f3a44d6d53e6835f727d6b99b7cdd3f1611"},
+    {file = "soxr-0.3.7-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:83c74ef6d61d7dcd81be26f91bee0a420f792f5c1982266f2a80e655f0650a98"},
+    {file = "soxr-0.3.7-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:cb1e14663a43fe88b8fbc287822a159028366a820abe1a0a9670fb53618cb47b"},
+    {file = "soxr-0.3.7-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:48acdfbcf870ab54f645b1cfd641bce92c1e3a67346c3bf0f6c0ad2873c1dd35"},
+    {file = "soxr-0.3.7-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ea663b76f2b0ec1576b8a43aef317aec080abc0a67a4015fcd9f3407039f260a"},
+    {file = "soxr-0.3.7-cp312-cp312-win_amd64.whl", hash = "sha256:42da0d9eb79c70e5a41917f1b48a032e241a48eb4a1bcea7c80577302ff26974"},
+    {file = "soxr-0.3.7-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:511c6b2279c8ddd83459d129d69f628f7aae4616ae0a1912963985bd89e35df7"},
+    {file = "soxr-0.3.7-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a37c518c0b5d70162956d808d6c2e249bae0672e414e0dcfc101e200d8c31f3c"},
+    {file = "soxr-0.3.7-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:27f2890528d2b2e358938ab660a6b8346802863f5b6b646204d7ff8ab0ca2c66"},
+    {file = "soxr-0.3.7-cp37-cp37m-win_amd64.whl", hash = "sha256:52467c8c012495544a6dcfcce6b5bcbbc653d24fe9bb33c0b6191acecdb5e297"},
+    {file = "soxr-0.3.7-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:ce12b93747958f2769d6b297e6e27c73d9ad635fe8104ef052bece9c8a322824"},
+    {file = "soxr-0.3.7-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:1cd65dc7b96ea3cb6c8c48e6020e859680556cc42dd3d4de44779530cce21037"},
+    {file = "soxr-0.3.7-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d994f1a7690b1b13ab639ea33e0c1d78415b64d88d6df4af705a9443f97b9687"},
+    {file = "soxr-0.3.7-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e87b58bc9e8c2caa16f07726f666bd043f0a49ca937baa803ce7708003b27833"},
+    {file = "soxr-0.3.7-cp38-cp38-win_amd64.whl", hash = "sha256:07f4c0c6125ea1482fa187ad5f007216712ee0a93586a9b2f80e79c0bf944cf7"},
+    {file = "soxr-0.3.7-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:e5267c3ba34d4b873d9bbe3a9e58418b01ae4fd04349a4f944d9943b9ddac0f7"},
+    {file = "soxr-0.3.7-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:6e39668c250e221db888cf3b290a16fbe10a702d9a4eb604a127f720040de583"},
+    {file = "soxr-0.3.7-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f8ceeb74e5a55d903cc286d3bd12c2d8f8c85d02894071e9ec92ab405430907c"},
+    {file = "soxr-0.3.7-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0eed6bf58192dd1bb93becd2444de4d712689713d727b32fd55623ae9aae7df7"},
+    {file = "soxr-0.3.7-cp39-cp39-win_amd64.whl", hash = "sha256:7221302b4547d02a3f38dd3cd15317ab2b78873c75921db5f4a070848f0c71be"},
+    {file = "soxr-0.3.7.tar.gz", hash = "sha256:436ddff00c6eb2c75b79c19cfdca7527b1e31b5fad738652f044045ba6258593"},
+]
+
+[package.dependencies]
+numpy = "*"
+
+[package.extras]
+docs = ["linkify-it-py", "myst-parser", "sphinx", "sphinx-book-theme"]
+test = ["pytest"]
+
+[[package]]
+name = "starlette"
+version = "0.35.1"
+description = "The little ASGI library that shines."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "starlette-0.35.1-py3-none-any.whl", hash = "sha256:50bbbda9baa098e361f398fda0928062abbaf1f54f4fadcbe17c092a01eb9a25"},
+    {file = "starlette-0.35.1.tar.gz", hash = "sha256:3e2639dac3520e4f58734ed22553f950d3f3cb1001cd2eaac4d57e8cdc5f66bc"},
+]
+
+[package.dependencies]
+anyio = ">=3.4.0,<5"
+
+[package.extras]
+full = ["httpx (>=0.22.0)", "itsdangerous", "jinja2", "python-multipart", "pyyaml"]
+
+[[package]]
+name = "sympy"
+version = "1.12"
+description = "Computer algebra system (CAS) in Python"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "sympy-1.12-py3-none-any.whl", hash = "sha256:c3588cd4295d0c0f603d0f2ae780587e64e2efeedb3521e46b9bb1d08d184fa5"},
+    {file = "sympy-1.12.tar.gz", hash = "sha256:ebf595c8dac3e0fdc4152c51878b498396ec7f30e7a914d6071e674d49420fb8"},
+]
+
+[package.dependencies]
+mpmath = ">=0.19"
+
+[[package]]
+name = "tabulate"
+version = "0.9.0"
+description = "Pretty-print tabular data"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "tabulate-0.9.0-py3-none-any.whl", hash = "sha256:024ca478df22e9340661486f85298cff5f6dcdba14f3813e8830015b9ed1948f"},
+    {file = "tabulate-0.9.0.tar.gz", hash = "sha256:0095b12bf5966de529c0feb1fa08671671b3368eec77d7ef7ab114be2c068b3c"},
+]
+
+[package.extras]
+widechars = ["wcwidth"]
+
+[[package]]
+name = "tensorboardx"
+version = "2.6.2.2"
+description = "TensorBoardX lets you watch Tensors Flow without Tensorflow"
+optional = false
+python-versions = "*"
+files = [
+    {file = "tensorboardX-2.6.2.2-py2.py3-none-any.whl", hash = "sha256:160025acbf759ede23fd3526ae9d9bfbfd8b68eb16c38a010ebe326dc6395db8"},
+    {file = "tensorboardX-2.6.2.2.tar.gz", hash = "sha256:c6476d7cd0d529b0b72f4acadb1269f9ed8b22f441e87a84f2a3b940bb87b666"},
+]
+
+[package.dependencies]
+numpy = "*"
+packaging = "*"
+protobuf = ">=3.20"
+
+[[package]]
+name = "threadpoolctl"
+version = "3.2.0"
+description = "threadpoolctl"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "threadpoolctl-3.2.0-py3-none-any.whl", hash = "sha256:2b7818516e423bdaebb97c723f86a7c6b0a83d3f3b0970328d66f4d9104dc032"},
+    {file = "threadpoolctl-3.2.0.tar.gz", hash = "sha256:c96a0ba3bdddeaca37dc4cc7344aafad41cdb8c313f74fdfe387a867bba93355"},
+]
+
+[[package]]
+name = "tomli"
+version = "2.0.1"
+description = "A lil' TOML parser"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
+    {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
+]
+
+[[package]]
+name = "torch"
+version = "2.1.2"
+description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
+optional = false
+python-versions = ">=3.8.0"
+files = [
+    {file = "torch-2.1.2-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:3a871edd6c02dae77ad810335c0833391c1a4ce49af21ea8cf0f6a5d2096eea8"},
+    {file = "torch-2.1.2-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:bef6996c27d8f6e92ea4e13a772d89611da0e103b48790de78131e308cf73076"},
+    {file = "torch-2.1.2-cp310-cp310-win_amd64.whl", hash = "sha256:0e13034fd5fb323cbbc29e56d0637a3791e50dd589616f40c79adfa36a5a35a1"},
+    {file = "torch-2.1.2-cp310-none-macosx_10_9_x86_64.whl", hash = "sha256:d9b535cad0df3d13997dbe8bd68ac33e0e3ae5377639c9881948e40794a61403"},
+    {file = "torch-2.1.2-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:f9a55d55af02826ebfbadf4e9b682f0f27766bc33df8236b48d28d705587868f"},
+    {file = "torch-2.1.2-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:a6ebbe517097ef289cc7952783588c72de071d4b15ce0f8b285093f0916b1162"},
+    {file = "torch-2.1.2-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:8f32ce591616a30304f37a7d5ea80b69ca9e1b94bba7f308184bf616fdaea155"},
+    {file = "torch-2.1.2-cp311-cp311-win_amd64.whl", hash = "sha256:e0ee6cf90c8970e05760f898d58f9ac65821c37ffe8b04269ec787aa70962b69"},
+    {file = "torch-2.1.2-cp311-none-macosx_10_9_x86_64.whl", hash = "sha256:76d37967c31c99548ad2c4d3f2cf191db48476f2e69b35a0937137116da356a1"},
+    {file = "torch-2.1.2-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:e2d83f07b4aac983453ea5bf8f9aa9dacf2278a8d31247f5d9037f37befc60e4"},
+    {file = "torch-2.1.2-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:f41fe0c7ecbf903a568c73486139a75cfab287a0f6c17ed0698fdea7a1e8641d"},
+    {file = "torch-2.1.2-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:e3225f47d50bb66f756fe9196a768055d1c26b02154eb1f770ce47a2578d3aa7"},
+    {file = "torch-2.1.2-cp38-cp38-win_amd64.whl", hash = "sha256:33d59cd03cb60106857f6c26b36457793637512998666ee3ce17311f217afe2b"},
+    {file = "torch-2.1.2-cp38-none-macosx_10_9_x86_64.whl", hash = "sha256:8e221deccd0def6c2badff6be403e0c53491805ed9915e2c029adbcdb87ab6b5"},
+    {file = "torch-2.1.2-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:05b18594f60a911a0c4f023f38a8bda77131fba5fd741bda626e97dcf5a3dd0a"},
+    {file = "torch-2.1.2-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:9ca96253b761e9aaf8e06fb30a66ee301aecbf15bb5a303097de1969077620b6"},
+    {file = "torch-2.1.2-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:d93ba70f67b08c2ae5598ee711cbc546a1bc8102cef938904b8c85c2089a51a0"},
+    {file = "torch-2.1.2-cp39-cp39-win_amd64.whl", hash = "sha256:255b50bc0608db177e6a3cc118961d77de7e5105f07816585fa6f191f33a9ff3"},
+    {file = "torch-2.1.2-cp39-none-macosx_10_9_x86_64.whl", hash = "sha256:6984cd5057c0c977b3c9757254e989d3f1124f4ce9d07caa6cb637783c71d42a"},
+    {file = "torch-2.1.2-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:bc195d7927feabc0eb7c110e457c955ed2ab616f3c7c28439dd4188cf589699f"},
+]
+
+[package.dependencies]
+filelock = "*"
+fsspec = "*"
+jinja2 = "*"
+networkx = "*"
+nvidia-cublas-cu12 = {version = "12.1.3.1", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-cupti-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-nvrtc-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-runtime-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cudnn-cu12 = {version = "8.9.2.26", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cufft-cu12 = {version = "11.0.2.54", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-curand-cu12 = {version = "10.3.2.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cusolver-cu12 = {version = "11.4.5.107", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cusparse-cu12 = {version = "12.1.0.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-nccl-cu12 = {version = "2.18.1", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-nvtx-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+sympy = "*"
+triton = {version = "2.1.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+typing-extensions = "*"
+
+[package.extras]
+dynamo = ["jinja2"]
+opt-einsum = ["opt-einsum (>=3.3)"]
+
+[[package]]
+name = "torchaudio"
+version = "2.1.2"
+description = "An audio package for PyTorch"
+optional = false
+python-versions = "*"
+files = [
+    {file = "torchaudio-2.1.2-cp310-cp310-macosx_10_13_x86_64.whl", hash = "sha256:06f8c02814e6cdd78626bbf44ad2bb8afa5b39ab650c6af18328a32311461058"},
+    {file = "torchaudio-2.1.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9d676673c1ce4dd11fca145e3a6cd9b4e5b897cffad0f617d2906f2d3fc8c3a9"},
+    {file = "torchaudio-2.1.2-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:23c1b34e98664a0ac239efd4e1a0af407b3dd0a86a5869114bae582c3e5437d7"},
+    {file = "torchaudio-2.1.2-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:f82657fc4ec3b473bf6c752c0ee62d7f511af9ef37e5143f8339ec049504d767"},
+    {file = "torchaudio-2.1.2-cp310-cp310-win_amd64.whl", hash = "sha256:683eaa721e016ca1f27bb28fa89feae37a6f7b98ff1ceee0d5e5aedd19bd982c"},
+    {file = "torchaudio-2.1.2-cp311-cp311-macosx_10_13_x86_64.whl", hash = "sha256:c1084eedf4ced1af9fdd18910690ff615f89baeb30b32030806543fbc6f3657e"},
+    {file = "torchaudio-2.1.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:860acc32e6507063f2c13d81e26718199e215f34a2bcd6c9609a25e9bf21aa36"},
+    {file = "torchaudio-2.1.2-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:50c651d60bde7a4e096bf376eddb9ea32da6e37c3827536d6e918798ad203dbf"},
+    {file = "torchaudio-2.1.2-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:9a6bade8a2495a724f4ee6acb5e86828ff4083dc6c7c57c6386b54a0ea7afe71"},
+    {file = "torchaudio-2.1.2-cp311-cp311-win_amd64.whl", hash = "sha256:47f322708c282e0b1b7548cdbe4e12451c531061761885d7c7fe2e479a4a3861"},
+    {file = "torchaudio-2.1.2-cp38-cp38-macosx_10_13_x86_64.whl", hash = "sha256:d0efd008c35dec962b80f5dce3468bd1b88301cf65152bbfa7f74c0005a17e89"},
+    {file = "torchaudio-2.1.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:30ad97112412592518953f3cc2cd1b6ae153d6563dd5bd9eab6a972315fe9d9e"},
+    {file = "torchaudio-2.1.2-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:c33e05c2305bc4d659aaf77a385433e3f8ac07ae235d3b15d6ef4ff995258746"},
+    {file = "torchaudio-2.1.2-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:ff7156b30eb05e9124286c30c80da84b93e227d009adb96eb19489600b459332"},
+    {file = "torchaudio-2.1.2-cp38-cp38-win_amd64.whl", hash = "sha256:dbaefae9ca0b208ce0157e0358cea8ab796c9e26a2c61c3d181246e4010b04d2"},
+    {file = "torchaudio-2.1.2-cp39-cp39-macosx_10_13_x86_64.whl", hash = "sha256:ae50dcf34d5c6f73180cf694195ee31194b9d6090328575c30a5960bc716fa52"},
+    {file = "torchaudio-2.1.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:14729cc9df52defa674fcf5ed4de0d6507038ef18012b96a2f56a77ed70676dd"},
+    {file = "torchaudio-2.1.2-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:03b4cf02ee468b25280f9593cca95a32b517a88512a1e5f41129e24cd0c17e64"},
+    {file = "torchaudio-2.1.2-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:b3bbb5324e705ded77616e546591b249ae7588d35a3e8c2c4c1d986a5ea51ef4"},
+    {file = "torchaudio-2.1.2-cp39-cp39-win_amd64.whl", hash = "sha256:03d2a3c9a806486f2d9646381a564a922a880b6df8f18336b6f0e4a0d8356743"},
+]
+
+[package.dependencies]
+torch = "2.1.2"
+
+[[package]]
+name = "torchcrepe"
+version = "0.0.22"
+description = "Pytorch implementation of CREPE pitch tracker"
+optional = false
+python-versions = "*"
+files = [
+    {file = "torchcrepe-0.0.22-py3-none-any.whl", hash = "sha256:5279c76c202cd7968e7d9a7ee2a5af9451b1a4338ed8e4ad385e357ad355fcff"},
+    {file = "torchcrepe-0.0.22.tar.gz", hash = "sha256:80afa152af0fce02c6d13071996b8c5aa3ded7110ef600b41150f267d54d10a2"},
+]
+
+[package.dependencies]
+librosa = ">=0.9.1"
+resampy = "*"
+scipy = "*"
+torch = "*"
+tqdm = "*"
+
+[[package]]
+name = "tqdm"
+version = "4.66.1"
+description = "Fast, Extensible Progress Meter"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "tqdm-4.66.1-py3-none-any.whl", hash = "sha256:d302b3c5b53d47bce91fea46679d9c3c6508cf6332229aa1e7d8653723793386"},
+    {file = "tqdm-4.66.1.tar.gz", hash = "sha256:d88e651f9db8d8551a62556d3cff9e3034274ca5d66e93197cf2490e2dcb69c7"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
+[package.extras]
+dev = ["pytest (>=6)", "pytest-cov", "pytest-timeout", "pytest-xdist"]
+notebook = ["ipywidgets (>=6)"]
+slack = ["slack-sdk"]
+telegram = ["requests"]
+
+[[package]]
+name = "triton"
+version = "2.1.0"
+description = "A language and compiler for custom Deep Learning operations"
+optional = false
+python-versions = "*"
+files = [
+    {file = "triton-2.1.0-0-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:66439923a30d5d48399b08a9eae10370f6c261a5ec864a64983bae63152d39d7"},
+    {file = "triton-2.1.0-0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:919b06453f0033ea52c13eaf7833de0e57db3178d23d4e04f9fc71c4f2c32bf8"},
+    {file = "triton-2.1.0-0-cp37-cp37m-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:ae4bb8a91de790e1866405211c4d618379781188f40d5c4c399766914e84cd94"},
+    {file = "triton-2.1.0-0-cp38-cp38-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:39f6fb6bdccb3e98f3152e3fbea724f1aeae7d749412bbb1fa9c441d474eba26"},
+    {file = "triton-2.1.0-0-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:21544e522c02005a626c8ad63d39bdff2f31d41069592919ef281e964ed26446"},
+    {file = "triton-2.1.0-0-pp37-pypy37_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:143582ca31dd89cd982bd3bf53666bab1c7527d41e185f9e3d8a3051ce1b663b"},
+    {file = "triton-2.1.0-0-pp38-pypy38_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:82fc5aeeedf6e36be4e4530cbdcba81a09d65c18e02f52dc298696d45721f3bd"},
+    {file = "triton-2.1.0-0-pp39-pypy39_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:81a96d110a738ff63339fc892ded095b31bd0d205e3aace262af8400d40b6fa8"},
+]
+
+[package.dependencies]
+filelock = "*"
+
+[package.extras]
+build = ["cmake (>=3.18)", "lit"]
+tests = ["autopep8", "flake8", "isort", "numpy", "pytest", "scipy (>=1.7.1)"]
+tutorials = ["matplotlib", "pandas", "tabulate"]
+
+[[package]]
+name = "typing-extensions"
+version = "4.9.0"
+description = "Backported and Experimental Type Hints for Python 3.8+"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "typing_extensions-4.9.0-py3-none-any.whl", hash = "sha256:af72aea155e91adfc61c3ae9e0e342dbc0cba726d6cba4b6c72c1f34e47291cd"},
+    {file = "typing_extensions-4.9.0.tar.gz", hash = "sha256:23478f88c37f27d76ac8aee6c905017a143b0b1b886c3c9f66bc2fd94f9f5783"},
+]
+
+[[package]]
+name = "urllib3"
+version = "2.1.0"
+description = "HTTP library with thread-safe connection pooling, file post, and more."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "urllib3-2.1.0-py3-none-any.whl", hash = "sha256:55901e917a5896a349ff771be919f8bd99aff50b79fe58fec595eb37bbc56bb3"},
+    {file = "urllib3-2.1.0.tar.gz", hash = "sha256:df7aa8afb0148fa78488e7899b2c59b5f4ffcfa82e6c54ccb9dd37c1d7b52d54"},
+]
+
+[package.extras]
+brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"]
+socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
+zstd = ["zstandard (>=0.18.0)"]
+
+[[package]]
+name = "uvicorn"
+version = "0.26.0"
+description = "The lightning-fast ASGI server."
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "uvicorn-0.26.0-py3-none-any.whl", hash = "sha256:cdb58ef6b8188c6c174994b2b1ba2150a9a8ae7ea5fb2f1b856b94a815d6071d"},
+    {file = "uvicorn-0.26.0.tar.gz", hash = "sha256:48bfd350fce3c5c57af5fb4995fded8fb50da3b4feb543eb18ad7e0d54589602"},
+]
+
+[package.dependencies]
+click = ">=7.0"
+h11 = ">=0.8"
+typing-extensions = {version = ">=4.0", markers = "python_version < \"3.11\""}
+
+[package.extras]
+standard = ["colorama (>=0.4)", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1)", "watchfiles (>=0.13)", "websockets (>=10.4)"]
+
+[extras]
+api = ["fastapi", "uvicorn"]
+
+[metadata]
+lock-version = "2.0"
+python-versions = "^3.10"
+content-hash = "41b40d268721bdd662df71e1bed565726440b3507ae703d6698cbefcf3c58e03"
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000000000000000000000000000000000000..6c53b68d77431dd6e91620490cf06404afed26a5
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,44 @@
+[tool.poetry]
+name = "rvc"
+version = "0.3.5"
+description = "An easy-to-use Voice Conversion framework based on VITS."
+authors = ["Ftps <ftpsflandre@gmail.com>"]
+readme = "README.md"
+
+[tool.poetry.urls]
+github = "https://github.com/RVC-Project/Retrieval-based-Voice-Conversion"
+
+[tool.poetry.dependencies]
+python = "^3.10"
+torch = "^2.1.0"
+#fairseq = "^0.12.2"
+fairseq = {git = "https://github.com/Tps-F/fairseq.git", branch="main"}
+soundfile = "^0.12.1"
+librosa = "^0.10.1"
+praat-parselmouth = "^0.4.3"
+pyworld = "^0.3.4"
+torchcrepe = "^0.0.22"
+av = "^11.0.0"
+faiss-cpu = "^1.7.4"
+python-dotenv = "^1.0.0"
+pydub = "^0.25.1"
+click = "^8.1.7"
+tensorboardx = "^2.6.2.2"
+poethepoet = "^0.24.4"
+uvicorn = "^0.26.0"
+fastapi = "^0.109.0"
+python-multipart = "^0.0.6"
+numba = "0.59.0rc1"
+
+[tool.poetry.extras]
+api = ["uvicorn", "fastapi"]
+
+[tool.poetry.scripts]
+rvc = "rvc.wrapper.cli.cli:main"
+
+[tool.poe.tasks]
+rvc-api = "uvicorn rvc.wrapper.api.api:app --host 0.0.0.0 --port 8000 --reload"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
diff --git a/rvc/__init__.py b/rvc/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/rvc/configs/__init__.py b/rvc/configs/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..42a128ce4e0bb16fd8187553ccdf346f735d0e48
--- /dev/null
+++ b/rvc/configs/__init__.py
@@ -0,0 +1 @@
+from rvc.configs.config import Config
diff --git a/rvc/configs/config.py b/rvc/configs/config.py
new file mode 100644
index 0000000000000000000000000000000000000000..d6824847181f5fc828366d5a2500208533d02e28
--- /dev/null
+++ b/rvc/configs/config.py
@@ -0,0 +1,197 @@
+import argparse
+import json
+import logging
+import os
+import sys
+from multiprocessing import cpu_count
+
+import torch
+
+try:
+    import intel_extension_for_pytorch as ipex
+
+    if torch.xpu.is_available():
+        from rvc.lib.ipex import ipex_init
+
+        ipex_init()
+except (ImportError, Exception):
+    pass
+
+logger: logging.Logger = logging.getLogger(__name__)
+
+
+version_config_list: list = [
+    os.path.join(root, file)
+    for root, dirs, files in os.walk(os.path.dirname(os.path.abspath(__file__)))
+    for file in files
+    if file.endswith(".json")
+]
+
+
+class Config:
+    def __new__(cls):
+        if not hasattr(cls, "_instance"):
+            cls._instance = super().__new__(cls)
+        return cls._instance
+
+    def __init__(self):
+        self.device: str = "cuda:0"
+        self.is_half: bool = True
+        self.use_jit: bool = False
+        self.n_cpu: int = cpu_count()
+        self.gpu_name: str | None = None
+        self.json_config = self.load_config_json()
+        self.gpu_mem: int | None = None
+        self.instead: str | None = None
+        (
+            self.python_cmd,
+            self.listen_port,
+            self.noparallel,
+            self.noautoopen,
+            self.dml,
+        ) = self.arg_parse()
+        self.x_pad, self.x_query, self.x_center, self.x_max = self.device_config()
+
+    @staticmethod
+    def load_config_json() -> dict:
+        return {
+            config_file: json.load(open(config_file, "r"))
+            for config_file in version_config_list
+        }
+
+    @staticmethod
+    def arg_parse() -> tuple:
+        parser: argparse.ArgumentParser = argparse.ArgumentParser()
+        parser.add_argument("--port", type=int, default=7865, help="Listen port")
+        parser.add_argument(
+            "--pycmd",
+            type=str,
+            default=sys.executable or "python",
+            help="Python command",
+        )
+        parser.add_argument(
+            "--noparallel", action="store_true", help="Disable parallel processing"
+        )
+        parser.add_argument(
+            "--noautoopen",
+            action="store_true",
+            help="Do not open in browser automatically",
+        )
+        parser.add_argument(
+            "--dml",
+            action="store_true",
+            help="torch_dml",
+        )
+        cmd_opts: argparse.Namespace
+        cmd_opts, _ = parser.parse_known_args()
+
+        cmd_opts.port = cmd_opts.port if 0 <= cmd_opts.port <= 65535 else 7865
+
+        return (
+            cmd_opts.pycmd,
+            cmd_opts.port,
+            cmd_opts.noparallel,
+            cmd_opts.noautoopen,
+            cmd_opts.dml,
+        )
+
+    @staticmethod
+    def has_mps() -> bool:
+        return torch.backends.mps.is_available() and not torch.zeros(1).to(
+            torch.device("mps")
+        )
+
+    @staticmethod
+    def has_xpu() -> bool:
+        return hasattr(torch, "xpu") and torch.xpu.is_available()
+
+    def params_config(self) -> tuple:
+        if self.gpu_mem is not None and self.gpu_mem <= 4:
+            x_pad = 1
+            x_query = 5
+            x_center = 30
+            x_max = 32
+        elif self.is_half:
+            # 6G PU_RAM conf
+            x_pad = 3
+            x_query = 10
+            x_center = 60
+            x_max = 65
+        else:
+            # 5G GPU_RAM conf
+            x_pad = 1
+            x_query = 6
+            x_center = 38
+            x_max = 41
+        return x_pad, x_query, x_center, x_max
+
+    def use_cuda(self) -> None:
+        if self.has_xpu():
+            self.device = self.instead = "xpu:0"
+            self.is_half = True
+        i_device = int(self.device.split(":")[-1])
+        self.gpu_name = torch.cuda.get_device_name(i_device)
+        if (
+            ("16" in self.gpu_name and "V100" not in self.gpu_name.upper())
+            or "P40" in self.gpu_name.upper()
+            or "P10" in self.gpu_name.upper()
+            or "1060" in self.gpu_name
+            or "1070" in self.gpu_name
+            or "1080" in self.gpu_name
+        ):
+            logger.info(f"Found GPU {self.gpu_name}, force to fp32")
+            self.is_half = False
+            self.use_fp32_config()
+        else:
+            logger.info(f"Found GPU {self.gpu_name}")
+        self.gpu_mem = int(
+            torch.cuda.get_device_properties(i_device).total_memory / 1024 / 1024 / 1024
+            + 0.4
+        )
+
+    def use_mps(self) -> None:
+        self.device = self.instead = "mps"
+        self.is_half = False
+        self.use_fp32_config()
+        self.params_config()
+
+    def use_dml(self) -> None:
+        import torch_directml
+
+        self.device = torch_directml.device(torch_directml.default_device())
+        self.is_half = False
+        self.params_config()
+
+    def use_cpu(self) -> None:
+        self.device = self.instead = "cpu"
+        self.is_half = False
+        self.use_fp32_config()
+        self.params_config()
+
+    def use_fp32_config(self) -> None:
+        for config_file, data in self.json_config.items():
+            try:
+                data["train"]["fp16_run"] = False
+                with open(config_file, "w") as json_file:
+                    json.dump(data, json_file, indent=4)
+            except Exception as e:
+                logger.info(f"Error updating {config_file}: {str(e)}")
+        logger.info("overwrite configs.json")
+
+    def device_config(self) -> tuple:
+        if torch.cuda.is_available():
+            self.use_cuda()
+        elif self.has_mps():
+            logger.info("No supported Nvidia GPU found")
+            self.use_mps()
+        elif self.dml:
+            self.use_dml()
+        else:
+            logger.info("No supported Nvidia GPU found")
+            self.device = self.instead = "cpu"
+            self.is_half = False
+            self.use_fp32_config()
+
+        logger.info(f"Use {self.dml or self.instead} instead")
+        logger.info(f"is_half:{self.is_half}, device:{self.device}")
+        return self.params_config()
diff --git a/rvc/configs/v1/32k.json b/rvc/configs/v1/32k.json
new file mode 100644
index 0000000000000000000000000000000000000000..d5f16d691ed798f4c974b431167c36269b2ce7d2
--- /dev/null
+++ b/rvc/configs/v1/32k.json
@@ -0,0 +1,46 @@
+{
+  "train": {
+    "log_interval": 200,
+    "seed": 1234,
+    "epochs": 20000,
+    "learning_rate": 1e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 4,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 12800,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "max_wav_value": 32768.0,
+    "sampling_rate": 32000,
+    "filter_length": 1024,
+    "hop_length": 320,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0,
+    "resblock": "1",
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+    "upsample_rates": [10,4,2,2,2],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [16,16,4,4,4],
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "spk_embed_dim": 109
+  }
+}
diff --git a/rvc/configs/v1/40k.json b/rvc/configs/v1/40k.json
new file mode 100644
index 0000000000000000000000000000000000000000..4ffc87b9e9725fcd59d81a68d41a61962213b777
--- /dev/null
+++ b/rvc/configs/v1/40k.json
@@ -0,0 +1,46 @@
+{
+  "train": {
+    "log_interval": 200,
+    "seed": 1234,
+    "epochs": 20000,
+    "learning_rate": 1e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 4,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 12800,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "max_wav_value": 32768.0,
+    "sampling_rate": 40000,
+    "filter_length": 2048,
+    "hop_length": 400,
+    "win_length": 2048,
+    "n_mel_channels": 125,
+    "mel_fmin": 0.0,
+    "mel_fmax": null
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0,
+    "resblock": "1",
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+    "upsample_rates": [10,10,2,2],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [16,16,4,4],
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "spk_embed_dim": 109
+  }
+}
diff --git a/rvc/configs/v1/48k.json b/rvc/configs/v1/48k.json
new file mode 100644
index 0000000000000000000000000000000000000000..2d0e05beb794f6f61b769b48c7ae728bf59e6335
--- /dev/null
+++ b/rvc/configs/v1/48k.json
@@ -0,0 +1,46 @@
+{
+  "train": {
+    "log_interval": 200,
+    "seed": 1234,
+    "epochs": 20000,
+    "learning_rate": 1e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 4,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 11520,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "max_wav_value": 32768.0,
+    "sampling_rate": 48000,
+    "filter_length": 2048,
+    "hop_length": 480,
+    "win_length": 2048,
+    "n_mel_channels": 128,
+    "mel_fmin": 0.0,
+    "mel_fmax": null
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0,
+    "resblock": "1",
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+    "upsample_rates": [10,6,2,2,2],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [16,16,4,4,4],
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "spk_embed_dim": 109
+  }
+}
diff --git a/rvc/configs/v2/32k.json b/rvc/configs/v2/32k.json
new file mode 100644
index 0000000000000000000000000000000000000000..70e534f4c641a5a2c8e5c1e172f61398ee97e6e0
--- /dev/null
+++ b/rvc/configs/v2/32k.json
@@ -0,0 +1,46 @@
+{
+  "train": {
+    "log_interval": 200,
+    "seed": 1234,
+    "epochs": 20000,
+    "learning_rate": 1e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 4,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 12800,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "max_wav_value": 32768.0,
+    "sampling_rate": 32000,
+    "filter_length": 1024,
+    "hop_length": 320,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0,
+    "resblock": "1",
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+    "upsample_rates": [10,8,2,2],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [20,16,4,4],
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "spk_embed_dim": 109
+  }
+}
diff --git a/rvc/configs/v2/48k.json b/rvc/configs/v2/48k.json
new file mode 100644
index 0000000000000000000000000000000000000000..75f770cdacff3467e9e925ed2393b480881d0303
--- /dev/null
+++ b/rvc/configs/v2/48k.json
@@ -0,0 +1,46 @@
+{
+  "train": {
+    "log_interval": 200,
+    "seed": 1234,
+    "epochs": 20000,
+    "learning_rate": 1e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 4,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 17280,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "max_wav_value": 32768.0,
+    "sampling_rate": 48000,
+    "filter_length": 2048,
+    "hop_length": 480,
+    "win_length": 2048,
+    "n_mel_channels": 128,
+    "mel_fmin": 0.0,
+    "mel_fmax": null
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0,
+    "resblock": "1",
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+    "upsample_rates": [12,10,2,2],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [24,20,4,4],
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "spk_embed_dim": 109
+  }
+}
diff --git a/rvc/lib/audio.py b/rvc/lib/audio.py
new file mode 100644
index 0000000000000000000000000000000000000000..9d2062554e2347c7b8352b2f2a90c1a85b98ff3e
--- /dev/null
+++ b/rvc/lib/audio.py
@@ -0,0 +1,70 @@
+import os
+import traceback
+from io import BytesIO
+
+import av
+import librosa
+import numpy as np
+
+
+def wav2(i, o, format):
+    inp = av.open(i, "rb")
+    if format == "m4a":
+        format = "mp4"
+    out = av.open(o, "wb", format=format)
+    if format == "ogg":
+        format = "libvorbis"
+    if format == "mp4":
+        format = "aac"
+
+    ostream = out.add_stream(format)
+
+    for frame in inp.decode(audio=0):
+        for p in ostream.encode(frame):
+            out.mux(p)
+
+    for p in ostream.encode(None):
+        out.mux(p)
+
+    out.close()
+    inp.close()
+
+
+def audio2(i, o, format, sr):
+    inp = av.open(i, "rb")
+    out = av.open(o, "wb", format=format)
+    if format == "ogg":
+        format = "libvorbis"
+    if format == "f32le":
+        format = "pcm_f32le"
+
+    ostream = out.add_stream(format, channels=1)
+    ostream.sample_rate = sr
+
+    for frame in inp.decode(audio=0):
+        for p in ostream.encode(frame):
+            out.mux(p)
+
+    out.close()
+    inp.close()
+
+
+def load_audio(file, sr):
+    if not os.path.exists(file):
+        raise RuntimeError(
+            "You input a wrong audio path that does not exists, please fix it!"
+        )
+    try:
+        with open(file, "rb") as f:
+            with BytesIO() as out:
+                audio2(f, out, "f32le", sr)
+                return np.frombuffer(out.getvalue(), np.float32).flatten()
+
+    except AttributeError:
+        audio = file[1] / 32768.0
+        if len(audio.shape) == 2:
+            audio = np.mean(audio, -1)
+        return librosa.resample(audio, orig_sr=file[0], target_sr=16000)
+
+    except Exception:
+        raise RuntimeError(traceback.format_exc())
diff --git a/rvc/lib/infer_pack/attentions.py b/rvc/lib/infer_pack/attentions.py
new file mode 100644
index 0000000000000000000000000000000000000000..0778c40c0d448a8182a9d0d1018e1f8a9014803f
--- /dev/null
+++ b/rvc/lib/infer_pack/attentions.py
@@ -0,0 +1,459 @@
+import copy
+import math
+from typing import Optional
+
+import numpy as np
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+from rvc.lib.infer_pack import commons, modules
+from rvc.lib.infer_pack.modules import LayerNorm
+
+
+class Encoder(nn.Module):
+    def __init__(
+        self,
+        hidden_channels,
+        filter_channels,
+        n_heads,
+        n_layers,
+        kernel_size=1,
+        p_dropout=0.0,
+        window_size=10,
+        **kwargs
+    ):
+        super(Encoder, self).__init__()
+        self.hidden_channels = hidden_channels
+        self.filter_channels = filter_channels
+        self.n_heads = n_heads
+        self.n_layers = int(n_layers)
+        self.kernel_size = kernel_size
+        self.p_dropout = p_dropout
+        self.window_size = window_size
+
+        self.drop = nn.Dropout(p_dropout)
+        self.attn_layers = nn.ModuleList()
+        self.norm_layers_1 = nn.ModuleList()
+        self.ffn_layers = nn.ModuleList()
+        self.norm_layers_2 = nn.ModuleList()
+        for i in range(self.n_layers):
+            self.attn_layers.append(
+                MultiHeadAttention(
+                    hidden_channels,
+                    hidden_channels,
+                    n_heads,
+                    p_dropout=p_dropout,
+                    window_size=window_size,
+                )
+            )
+            self.norm_layers_1.append(LayerNorm(hidden_channels))
+            self.ffn_layers.append(
+                FFN(
+                    hidden_channels,
+                    hidden_channels,
+                    filter_channels,
+                    kernel_size,
+                    p_dropout=p_dropout,
+                )
+            )
+            self.norm_layers_2.append(LayerNorm(hidden_channels))
+
+    def forward(self, x, x_mask):
+        attn_mask = x_mask.unsqueeze(2) * x_mask.unsqueeze(-1)
+        x = x * x_mask
+        zippep = zip(
+            self.attn_layers, self.norm_layers_1, self.ffn_layers, self.norm_layers_2
+        )
+        for attn_layers, norm_layers_1, ffn_layers, norm_layers_2 in zippep:
+            y = attn_layers(x, x, attn_mask)
+            y = self.drop(y)
+            x = norm_layers_1(x + y)
+
+            y = ffn_layers(x, x_mask)
+            y = self.drop(y)
+            x = norm_layers_2(x + y)
+        x = x * x_mask
+        return x
+
+
+class Decoder(nn.Module):
+    def __init__(
+        self,
+        hidden_channels,
+        filter_channels,
+        n_heads,
+        n_layers,
+        kernel_size=1,
+        p_dropout=0.0,
+        proximal_bias=False,
+        proximal_init=True,
+        **kwargs
+    ):
+        super(Decoder, self).__init__()
+        self.hidden_channels = hidden_channels
+        self.filter_channels = filter_channels
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.kernel_size = kernel_size
+        self.p_dropout = p_dropout
+        self.proximal_bias = proximal_bias
+        self.proximal_init = proximal_init
+
+        self.drop = nn.Dropout(p_dropout)
+        self.self_attn_layers = nn.ModuleList()
+        self.norm_layers_0 = nn.ModuleList()
+        self.encdec_attn_layers = nn.ModuleList()
+        self.norm_layers_1 = nn.ModuleList()
+        self.ffn_layers = nn.ModuleList()
+        self.norm_layers_2 = nn.ModuleList()
+        for i in range(self.n_layers):
+            self.self_attn_layers.append(
+                MultiHeadAttention(
+                    hidden_channels,
+                    hidden_channels,
+                    n_heads,
+                    p_dropout=p_dropout,
+                    proximal_bias=proximal_bias,
+                    proximal_init=proximal_init,
+                )
+            )
+            self.norm_layers_0.append(LayerNorm(hidden_channels))
+            self.encdec_attn_layers.append(
+                MultiHeadAttention(
+                    hidden_channels, hidden_channels, n_heads, p_dropout=p_dropout
+                )
+            )
+            self.norm_layers_1.append(LayerNorm(hidden_channels))
+            self.ffn_layers.append(
+                FFN(
+                    hidden_channels,
+                    hidden_channels,
+                    filter_channels,
+                    kernel_size,
+                    p_dropout=p_dropout,
+                    causal=True,
+                )
+            )
+            self.norm_layers_2.append(LayerNorm(hidden_channels))
+
+    def forward(self, x, x_mask, h, h_mask):
+        """
+        x: decoder input
+        h: encoder output
+        """
+        self_attn_mask = commons.subsequent_mask(x_mask.size(2)).to(
+            device=x.device, dtype=x.dtype
+        )
+        encdec_attn_mask = h_mask.unsqueeze(2) * x_mask.unsqueeze(-1)
+        x = x * x_mask
+        for i in range(self.n_layers):
+            y = self.self_attn_layers[i](x, x, self_attn_mask)
+            y = self.drop(y)
+            x = self.norm_layers_0[i](x + y)
+
+            y = self.encdec_attn_layers[i](x, h, encdec_attn_mask)
+            y = self.drop(y)
+            x = self.norm_layers_1[i](x + y)
+
+            y = self.ffn_layers[i](x, x_mask)
+            y = self.drop(y)
+            x = self.norm_layers_2[i](x + y)
+        x = x * x_mask
+        return x
+
+
+class MultiHeadAttention(nn.Module):
+    def __init__(
+        self,
+        channels,
+        out_channels,
+        n_heads,
+        p_dropout=0.0,
+        window_size=None,
+        heads_share=True,
+        block_length=None,
+        proximal_bias=False,
+        proximal_init=False,
+    ):
+        super(MultiHeadAttention, self).__init__()
+        assert channels % n_heads == 0
+
+        self.channels = channels
+        self.out_channels = out_channels
+        self.n_heads = n_heads
+        self.p_dropout = p_dropout
+        self.window_size = window_size
+        self.heads_share = heads_share
+        self.block_length = block_length
+        self.proximal_bias = proximal_bias
+        self.proximal_init = proximal_init
+        self.attn = None
+
+        self.k_channels = channels // n_heads
+        self.conv_q = nn.Conv1d(channels, channels, 1)
+        self.conv_k = nn.Conv1d(channels, channels, 1)
+        self.conv_v = nn.Conv1d(channels, channels, 1)
+        self.conv_o = nn.Conv1d(channels, out_channels, 1)
+        self.drop = nn.Dropout(p_dropout)
+
+        if window_size is not None:
+            n_heads_rel = 1 if heads_share else n_heads
+            rel_stddev = self.k_channels**-0.5
+            self.emb_rel_k = nn.Parameter(
+                torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels)
+                * rel_stddev
+            )
+            self.emb_rel_v = nn.Parameter(
+                torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels)
+                * rel_stddev
+            )
+
+        nn.init.xavier_uniform_(self.conv_q.weight)
+        nn.init.xavier_uniform_(self.conv_k.weight)
+        nn.init.xavier_uniform_(self.conv_v.weight)
+        if proximal_init:
+            with torch.no_grad():
+                self.conv_k.weight.copy_(self.conv_q.weight)
+                self.conv_k.bias.copy_(self.conv_q.bias)
+
+    def forward(
+        self, x: torch.Tensor, c: torch.Tensor, attn_mask: Optional[torch.Tensor] = None
+    ):
+        q = self.conv_q(x)
+        k = self.conv_k(c)
+        v = self.conv_v(c)
+
+        x, _ = self.attention(q, k, v, mask=attn_mask)
+
+        x = self.conv_o(x)
+        return x
+
+    def attention(
+        self,
+        query: torch.Tensor,
+        key: torch.Tensor,
+        value: torch.Tensor,
+        mask: Optional[torch.Tensor] = None,
+    ):
+        # reshape [b, d, t] -> [b, n_h, t, d_k]
+        b, d, t_s = key.size()
+        t_t = query.size(2)
+        query = query.view(b, self.n_heads, self.k_channels, t_t).transpose(2, 3)
+        key = key.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3)
+        value = value.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3)
+
+        scores = torch.matmul(query / math.sqrt(self.k_channels), key.transpose(-2, -1))
+        if self.window_size is not None:
+            assert (
+                t_s == t_t
+            ), "Relative attention is only available for self-attention."
+            key_relative_embeddings = self._get_relative_embeddings(self.emb_rel_k, t_s)
+            rel_logits = self._matmul_with_relative_keys(
+                query / math.sqrt(self.k_channels), key_relative_embeddings
+            )
+            scores_local = self._relative_position_to_absolute_position(rel_logits)
+            scores = scores + scores_local
+        if self.proximal_bias:
+            assert t_s == t_t, "Proximal bias is only available for self-attention."
+            scores = scores + self._attention_bias_proximal(t_s).to(
+                device=scores.device, dtype=scores.dtype
+            )
+        if mask is not None:
+            scores = scores.masked_fill(mask == 0, -1e4)
+            if self.block_length is not None:
+                assert (
+                    t_s == t_t
+                ), "Local attention is only available for self-attention."
+                block_mask = (
+                    torch.ones_like(scores)
+                    .triu(-self.block_length)
+                    .tril(self.block_length)
+                )
+                scores = scores.masked_fill(block_mask == 0, -1e4)
+        p_attn = F.softmax(scores, dim=-1)  # [b, n_h, t_t, t_s]
+        p_attn = self.drop(p_attn)
+        output = torch.matmul(p_attn, value)
+        if self.window_size is not None:
+            relative_weights = self._absolute_position_to_relative_position(p_attn)
+            value_relative_embeddings = self._get_relative_embeddings(
+                self.emb_rel_v, t_s
+            )
+            output = output + self._matmul_with_relative_values(
+                relative_weights, value_relative_embeddings
+            )
+        output = (
+            output.transpose(2, 3).contiguous().view(b, d, t_t)
+        )  # [b, n_h, t_t, d_k] -> [b, d, t_t]
+        return output, p_attn
+
+    def _matmul_with_relative_values(self, x, y):
+        """
+        x: [b, h, l, m]
+        y: [h or 1, m, d]
+        ret: [b, h, l, d]
+        """
+        ret = torch.matmul(x, y.unsqueeze(0))
+        return ret
+
+    def _matmul_with_relative_keys(self, x, y):
+        """
+        x: [b, h, l, d]
+        y: [h or 1, m, d]
+        ret: [b, h, l, m]
+        """
+        ret = torch.matmul(x, y.unsqueeze(0).transpose(-2, -1))
+        return ret
+
+    def _get_relative_embeddings(self, relative_embeddings, length: int):
+        max_relative_position = 2 * self.window_size + 1
+        # Pad first before slice to avoid using cond ops.
+        pad_length: int = max(length - (self.window_size + 1), 0)
+        slice_start_position = max((self.window_size + 1) - length, 0)
+        slice_end_position = slice_start_position + 2 * length - 1
+        if pad_length > 0:
+            padded_relative_embeddings = F.pad(
+                relative_embeddings,
+                # commons.convert_pad_shape([[0, 0], [pad_length, pad_length], [0, 0]]),
+                [0, 0, pad_length, pad_length, 0, 0],
+            )
+        else:
+            padded_relative_embeddings = relative_embeddings
+        used_relative_embeddings = padded_relative_embeddings[
+            :, slice_start_position:slice_end_position
+        ]
+        return used_relative_embeddings
+
+    def _relative_position_to_absolute_position(self, x):
+        """
+        x: [b, h, l, 2*l-1]
+        ret: [b, h, l, l]
+        """
+        batch, heads, length, _ = x.size()
+        # Concat columns of pad to shift from relative to absolute indexing.
+        x = F.pad(
+            x,
+            #   commons.convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, 1]])
+            [0, 1, 0, 0, 0, 0, 0, 0],
+        )
+
+        # Concat extra elements so to add up to shape (len+1, 2*len-1).
+        x_flat = x.view([batch, heads, length * 2 * length])
+        x_flat = F.pad(
+            x_flat,
+            # commons.convert_pad_shape([[0, 0], [0, 0], [0, int(length) - 1]])
+            [0, int(length) - 1, 0, 0, 0, 0],
+        )
+
+        # Reshape and slice out the padded elements.
+        x_final = x_flat.view([batch, heads, length + 1, 2 * length - 1])[
+            :, :, :length, length - 1 :
+        ]
+        return x_final
+
+    def _absolute_position_to_relative_position(self, x):
+        """
+        x: [b, h, l, l]
+        ret: [b, h, l, 2*l-1]
+        """
+        batch, heads, length, _ = x.size()
+        # padd along column
+        x = F.pad(
+            x,
+            # commons.convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, int(length) - 1]])
+            [0, int(length) - 1, 0, 0, 0, 0, 0, 0],
+        )
+        x_flat = x.view([batch, heads, int(length**2) + int(length * (length - 1))])
+        # add 0's in the beginning that will skew the elements after reshape
+        x_flat = F.pad(
+            x_flat,
+            #    commons.convert_pad_shape([[0, 0], [0, 0], [int(length), 0]])
+            [length, 0, 0, 0, 0, 0],
+        )
+        x_final = x_flat.view([batch, heads, length, 2 * length])[:, :, :, 1:]
+        return x_final
+
+    def _attention_bias_proximal(self, length: int):
+        """Bias for self-attention to encourage attention to close positions.
+        Args:
+          length: an integer scalar.
+        Returns:
+          a Tensor with shape [1, 1, length, length]
+        """
+        r = torch.arange(length, dtype=torch.float32)
+        diff = torch.unsqueeze(r, 0) - torch.unsqueeze(r, 1)
+        return torch.unsqueeze(torch.unsqueeze(-torch.log1p(torch.abs(diff)), 0), 0)
+
+
+class FFN(nn.Module):
+    def __init__(
+        self,
+        in_channels,
+        out_channels,
+        filter_channels,
+        kernel_size,
+        p_dropout=0.0,
+        activation: str = None,
+        causal=False,
+    ):
+        super(FFN, self).__init__()
+        self.in_channels = in_channels
+        self.out_channels = out_channels
+        self.filter_channels = filter_channels
+        self.kernel_size = kernel_size
+        self.p_dropout = p_dropout
+        self.activation = activation
+        self.causal = causal
+        self.is_activation = True if activation == "gelu" else False
+        # if causal:
+        #     self.padding = self._causal_padding
+        # else:
+        #     self.padding = self._same_padding
+
+        self.conv_1 = nn.Conv1d(in_channels, filter_channels, kernel_size)
+        self.conv_2 = nn.Conv1d(filter_channels, out_channels, kernel_size)
+        self.drop = nn.Dropout(p_dropout)
+
+    def padding(self, x: torch.Tensor, x_mask: torch.Tensor) -> torch.Tensor:
+        if self.causal:
+            padding = self._causal_padding(x * x_mask)
+        else:
+            padding = self._same_padding(x * x_mask)
+        return padding
+
+    def forward(self, x: torch.Tensor, x_mask: torch.Tensor):
+        x = self.conv_1(self.padding(x, x_mask))
+        if self.is_activation:
+            x = x * torch.sigmoid(1.702 * x)
+        else:
+            x = torch.relu(x)
+        x = self.drop(x)
+
+        x = self.conv_2(self.padding(x, x_mask))
+        return x * x_mask
+
+    def _causal_padding(self, x):
+        if self.kernel_size == 1:
+            return x
+        pad_l: int = self.kernel_size - 1
+        pad_r: int = 0
+        # padding = [[0, 0], [0, 0], [pad_l, pad_r]]
+        x = F.pad(
+            x,
+            #   commons.convert_pad_shape(padding)
+            [pad_l, pad_r, 0, 0, 0, 0],
+        )
+        return x
+
+    def _same_padding(self, x):
+        if self.kernel_size == 1:
+            return x
+        pad_l: int = (self.kernel_size - 1) // 2
+        pad_r: int = self.kernel_size // 2
+        # padding = [[0, 0], [0, 0], [pad_l, pad_r]]
+        x = F.pad(
+            x,
+            #   commons.convert_pad_shape(padding)
+            [pad_l, pad_r, 0, 0, 0, 0],
+        )
+        return x
diff --git a/rvc/lib/infer_pack/commons.py b/rvc/lib/infer_pack/commons.py
new file mode 100644
index 0000000000000000000000000000000000000000..85594bebf76a9c6893cc47da01fbf91bcd1edf0e
--- /dev/null
+++ b/rvc/lib/infer_pack/commons.py
@@ -0,0 +1,172 @@
+import math
+from typing import List, Optional
+
+import numpy as np
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+
+def init_weights(m, mean=0.0, std=0.01):
+    classname = m.__class__.__name__
+    if classname.find("Conv") != -1:
+        m.weight.data.normal_(mean, std)
+
+
+def get_padding(kernel_size, dilation=1):
+    return int((kernel_size * dilation - dilation) / 2)
+
+
+# def convert_pad_shape(pad_shape):
+#     l = pad_shape[::-1]
+#     pad_shape = [item for sublist in l for item in sublist]
+#     return pad_shape
+
+
+def kl_divergence(m_p, logs_p, m_q, logs_q):
+    """KL(P||Q)"""
+    kl = (logs_q - logs_p) - 0.5
+    kl += (
+        0.5 * (torch.exp(2.0 * logs_p) + ((m_p - m_q) ** 2)) * torch.exp(-2.0 * logs_q)
+    )
+    return kl
+
+
+def rand_gumbel(shape):
+    """Sample from the Gumbel distribution, protect from overflows."""
+    uniform_samples = torch.rand(shape) * 0.99998 + 0.00001
+    return -torch.log(-torch.log(uniform_samples))
+
+
+def rand_gumbel_like(x):
+    g = rand_gumbel(x.size()).to(dtype=x.dtype, device=x.device)
+    return g
+
+
+def slice_segments(x, ids_str, segment_size=4):
+    ret = torch.zeros_like(x[:, :, :segment_size])
+    for i in range(x.size(0)):
+        idx_str = ids_str[i]
+        idx_end = idx_str + segment_size
+        ret[i] = x[i, :, idx_str:idx_end]
+    return ret
+
+
+def slice_segments2(x, ids_str, segment_size=4):
+    ret = torch.zeros_like(x[:, :segment_size])
+    for i in range(x.size(0)):
+        idx_str = ids_str[i]
+        idx_end = idx_str + segment_size
+        ret[i] = x[i, idx_str:idx_end]
+    return ret
+
+
+def rand_slice_segments(x, x_lengths=None, segment_size=4):
+    b, d, t = x.size()
+    if x_lengths is None:
+        x_lengths = t
+    ids_str_max = x_lengths - segment_size + 1
+    ids_str = (torch.rand([b]).to(device=x.device) * ids_str_max).to(dtype=torch.long)
+    ret = slice_segments(x, ids_str, segment_size)
+    return ret, ids_str
+
+
+def get_timing_signal_1d(length, channels, min_timescale=1.0, max_timescale=1.0e4):
+    position = torch.arange(length, dtype=torch.float)
+    num_timescales = channels // 2
+    log_timescale_increment = math.log(float(max_timescale) / float(min_timescale)) / (
+        num_timescales - 1
+    )
+    inv_timescales = min_timescale * torch.exp(
+        torch.arange(num_timescales, dtype=torch.float) * -log_timescale_increment
+    )
+    scaled_time = position.unsqueeze(0) * inv_timescales.unsqueeze(1)
+    signal = torch.cat([torch.sin(scaled_time), torch.cos(scaled_time)], 0)
+    signal = F.pad(signal, [0, 0, 0, channels % 2])
+    signal = signal.view(1, channels, length)
+    return signal
+
+
+def add_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4):
+    b, channels, length = x.size()
+    signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale)
+    return x + signal.to(dtype=x.dtype, device=x.device)
+
+
+def cat_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4, axis=1):
+    b, channels, length = x.size()
+    signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale)
+    return torch.cat([x, signal.to(dtype=x.dtype, device=x.device)], axis)
+
+
+def subsequent_mask(length):
+    mask = torch.tril(torch.ones(length, length)).unsqueeze(0).unsqueeze(0)
+    return mask
+
+
+@torch.jit.script
+def fused_add_tanh_sigmoid_multiply(input_a, input_b, n_channels):
+    n_channels_int = n_channels[0]
+    in_act = input_a + input_b
+    t_act = torch.tanh(in_act[:, :n_channels_int, :])
+    s_act = torch.sigmoid(in_act[:, n_channels_int:, :])
+    acts = t_act * s_act
+    return acts
+
+
+# def convert_pad_shape(pad_shape):
+#     l = pad_shape[::-1]
+#     pad_shape = [item for sublist in l for item in sublist]
+#     return pad_shape
+
+
+def convert_pad_shape(pad_shape: List[List[int]]) -> List[int]:
+    return torch.tensor(pad_shape).flip(0).reshape(-1).int().tolist()
+
+
+def shift_1d(x):
+    x = F.pad(x, convert_pad_shape([[0, 0], [0, 0], [1, 0]]))[:, :, :-1]
+    return x
+
+
+def sequence_mask(length: torch.Tensor, max_length: Optional[int] = None):
+    if max_length is None:
+        max_length = length.max()
+    x = torch.arange(max_length, dtype=length.dtype, device=length.device)
+    return x.unsqueeze(0) < length.unsqueeze(1)
+
+
+def generate_path(duration, mask):
+    """
+    duration: [b, 1, t_x]
+    mask: [b, 1, t_y, t_x]
+    """
+    device = duration.device
+
+    b, _, t_y, t_x = mask.shape
+    cum_duration = torch.cumsum(duration, -1)
+
+    cum_duration_flat = cum_duration.view(b * t_x)
+    path = sequence_mask(cum_duration_flat, t_y).to(mask.dtype)
+    path = path.view(b, t_x, t_y)
+    path = path - F.pad(path, convert_pad_shape([[0, 0], [1, 0], [0, 0]]))[:, :-1]
+    path = path.unsqueeze(1).transpose(2, 3) * mask
+    return path
+
+
+def clip_grad_value_(parameters, clip_value, norm_type=2):
+    if isinstance(parameters, torch.Tensor):
+        parameters = [parameters]
+    parameters = list(filter(lambda p: p.grad is not None, parameters))
+    norm_type = float(norm_type)
+    if clip_value is not None:
+        clip_value = float(clip_value)
+
+    total_norm = 0
+    for p in parameters:
+        param_norm = p.grad.data.norm(norm_type)
+        total_norm += param_norm.item() ** norm_type
+        if clip_value is not None:
+            p.grad.data.clamp_(min=-clip_value, max=clip_value)
+    total_norm = total_norm ** (1.0 / norm_type)
+    return total_norm
diff --git a/rvc/lib/infer_pack/models.py b/rvc/lib/infer_pack/models.py
new file mode 100644
index 0000000000000000000000000000000000000000..7fb3d824b86219acbfe8378d20b45aa15a2532b8
--- /dev/null
+++ b/rvc/lib/infer_pack/models.py
@@ -0,0 +1,1426 @@
+import logging
+import math
+from typing import Optional
+
+logger = logging.getLogger(__name__)
+
+import numpy as np
+import torch
+from torch import nn
+from torch.nn import AvgPool1d, Conv1d, Conv2d, ConvTranspose1d
+from torch.nn import functional as F
+from torch.nn.utils import remove_weight_norm, spectral_norm, weight_norm
+
+from rvc.lib.infer_pack import attentions, commons, modules
+from rvc.lib.infer_pack.commons import get_padding, init_weights
+
+has_xpu = bool(hasattr(torch, "xpu") and torch.xpu.is_available())
+
+
+class TextEncoder256(nn.Module):
+    def __init__(
+        self,
+        out_channels,
+        hidden_channels,
+        filter_channels,
+        n_heads,
+        n_layers,
+        kernel_size,
+        p_dropout,
+        f0=True,
+    ):
+        super(TextEncoder256, self).__init__()
+        self.out_channels = out_channels
+        self.hidden_channels = hidden_channels
+        self.filter_channels = filter_channels
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.kernel_size = kernel_size
+        self.p_dropout = float(p_dropout)
+        self.emb_phone = nn.Linear(256, hidden_channels)
+        self.lrelu = nn.LeakyReLU(0.1, inplace=True)
+        if f0 == True:
+            self.emb_pitch = nn.Embedding(256, hidden_channels)  # pitch 256
+        self.encoder = attentions.Encoder(
+            hidden_channels,
+            filter_channels,
+            n_heads,
+            n_layers,
+            kernel_size,
+            float(p_dropout),
+        )
+        self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
+
+    def forward(
+        self, phone: torch.Tensor, pitch: Optional[torch.Tensor], lengths: torch.Tensor
+    ):
+        if pitch is None:
+            x = self.emb_phone(phone)
+        else:
+            x = self.emb_phone(phone) + self.emb_pitch(pitch)
+        x = x * math.sqrt(self.hidden_channels)  # [b, t, h]
+        x = self.lrelu(x)
+        x = torch.transpose(x, 1, -1)  # [b, h, t]
+        x_mask = torch.unsqueeze(commons.sequence_mask(lengths, x.size(2)), 1).to(
+            x.dtype
+        )
+        x = self.encoder(x * x_mask, x_mask)
+        stats = self.proj(x) * x_mask
+
+        m, logs = torch.split(stats, self.out_channels, dim=1)
+        return m, logs, x_mask
+
+
+class TextEncoder768(nn.Module):
+    def __init__(
+        self,
+        out_channels,
+        hidden_channels,
+        filter_channels,
+        n_heads,
+        n_layers,
+        kernel_size,
+        p_dropout,
+        f0=True,
+    ):
+        super(TextEncoder768, self).__init__()
+        self.out_channels = out_channels
+        self.hidden_channels = hidden_channels
+        self.filter_channels = filter_channels
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.kernel_size = kernel_size
+        self.p_dropout = float(p_dropout)
+        self.emb_phone = nn.Linear(768, hidden_channels)
+        self.lrelu = nn.LeakyReLU(0.1, inplace=True)
+        if f0 == True:
+            self.emb_pitch = nn.Embedding(256, hidden_channels)  # pitch 256
+        self.encoder = attentions.Encoder(
+            hidden_channels,
+            filter_channels,
+            n_heads,
+            n_layers,
+            kernel_size,
+            float(p_dropout),
+        )
+        self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
+
+    def forward(self, phone: torch.Tensor, pitch: torch.Tensor, lengths: torch.Tensor):
+        if pitch is None:
+            x = self.emb_phone(phone)
+        else:
+            x = self.emb_phone(phone) + self.emb_pitch(pitch)
+        x = x * math.sqrt(self.hidden_channels)  # [b, t, h]
+        x = self.lrelu(x)
+        x = torch.transpose(x, 1, -1)  # [b, h, t]
+        x_mask = torch.unsqueeze(commons.sequence_mask(lengths, x.size(2)), 1).to(
+            x.dtype
+        )
+        x = self.encoder(x * x_mask, x_mask)
+        stats = self.proj(x) * x_mask
+
+        m, logs = torch.split(stats, self.out_channels, dim=1)
+        return m, logs, x_mask
+
+
+class ResidualCouplingBlock(nn.Module):
+    def __init__(
+        self,
+        channels,
+        hidden_channels,
+        kernel_size,
+        dilation_rate,
+        n_layers,
+        n_flows=4,
+        gin_channels=0,
+    ):
+        super(ResidualCouplingBlock, self).__init__()
+        self.channels = channels
+        self.hidden_channels = hidden_channels
+        self.kernel_size = kernel_size
+        self.dilation_rate = dilation_rate
+        self.n_layers = n_layers
+        self.n_flows = n_flows
+        self.gin_channels = gin_channels
+
+        self.flows = nn.ModuleList()
+        for i in range(n_flows):
+            self.flows.append(
+                modules.ResidualCouplingLayer(
+                    channels,
+                    hidden_channels,
+                    kernel_size,
+                    dilation_rate,
+                    n_layers,
+                    gin_channels=gin_channels,
+                    mean_only=True,
+                )
+            )
+            self.flows.append(modules.Flip())
+
+    def forward(
+        self,
+        x: torch.Tensor,
+        x_mask: torch.Tensor,
+        g: Optional[torch.Tensor] = None,
+        reverse: bool = False,
+    ):
+        if not reverse:
+            for flow in self.flows:
+                x, _ = flow(x, x_mask, g=g, reverse=reverse)
+        else:
+            for flow in self.flows[::-1]:
+                x, _ = flow.forward(x, x_mask, g=g, reverse=reverse)
+        return x
+
+    def remove_weight_norm(self):
+        for i in range(self.n_flows):
+            self.flows[i * 2].remove_weight_norm()
+
+    def __prepare_scriptable__(self):
+        for i in range(self.n_flows):
+            for hook in self.flows[i * 2]._forward_pre_hooks.values():
+                if (
+                    hook.__module__ == "torch.nn.utils.weight_norm"
+                    and hook.__class__.__name__ == "WeightNorm"
+                ):
+                    torch.nn.utils.remove_weight_norm(self.flows[i * 2])
+
+        return self
+
+
+class PosteriorEncoder(nn.Module):
+    def __init__(
+        self,
+        in_channels,
+        out_channels,
+        hidden_channels,
+        kernel_size,
+        dilation_rate,
+        n_layers,
+        gin_channels=0,
+    ):
+        super(PosteriorEncoder, self).__init__()
+        self.in_channels = in_channels
+        self.out_channels = out_channels
+        self.hidden_channels = hidden_channels
+        self.kernel_size = kernel_size
+        self.dilation_rate = dilation_rate
+        self.n_layers = n_layers
+        self.gin_channels = gin_channels
+
+        self.pre = nn.Conv1d(in_channels, hidden_channels, 1)
+        self.enc = modules.WN(
+            hidden_channels,
+            kernel_size,
+            dilation_rate,
+            n_layers,
+            gin_channels=gin_channels,
+        )
+        self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
+
+    def forward(
+        self, x: torch.Tensor, x_lengths: torch.Tensor, g: Optional[torch.Tensor] = None
+    ):
+        x_mask = torch.unsqueeze(commons.sequence_mask(x_lengths, x.size(2)), 1).to(
+            x.dtype
+        )
+        x = self.pre(x) * x_mask
+        x = self.enc(x, x_mask, g=g)
+        stats = self.proj(x) * x_mask
+        m, logs = torch.split(stats, self.out_channels, dim=1)
+        z = (m + torch.randn_like(m) * torch.exp(logs)) * x_mask
+        return z, m, logs, x_mask
+
+    def remove_weight_norm(self):
+        self.enc.remove_weight_norm()
+
+    def __prepare_scriptable__(self):
+        for hook in self.enc._forward_pre_hooks.values():
+            if (
+                hook.__module__ == "torch.nn.utils.weight_norm"
+                and hook.__class__.__name__ == "WeightNorm"
+            ):
+                torch.nn.utils.remove_weight_norm(self.enc)
+        return self
+
+
+class Generator(torch.nn.Module):
+    def __init__(
+        self,
+        initial_channel,
+        resblock,
+        resblock_kernel_sizes,
+        resblock_dilation_sizes,
+        upsample_rates,
+        upsample_initial_channel,
+        upsample_kernel_sizes,
+        gin_channels=0,
+    ):
+        super(Generator, self).__init__()
+        self.num_kernels = len(resblock_kernel_sizes)
+        self.num_upsamples = len(upsample_rates)
+        self.conv_pre = Conv1d(
+            initial_channel, upsample_initial_channel, 7, 1, padding=3
+        )
+        resblock = modules.ResBlock1 if resblock == "1" else modules.ResBlock2
+
+        self.ups = nn.ModuleList()
+        for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
+            self.ups.append(
+                weight_norm(
+                    ConvTranspose1d(
+                        upsample_initial_channel // (2**i),
+                        upsample_initial_channel // (2 ** (i + 1)),
+                        k,
+                        u,
+                        padding=(k - u) // 2,
+                    )
+                )
+            )
+
+        self.resblocks = nn.ModuleList()
+        for i in range(len(self.ups)):
+            ch = upsample_initial_channel // (2 ** (i + 1))
+            for j, (k, d) in enumerate(
+                zip(resblock_kernel_sizes, resblock_dilation_sizes)
+            ):
+                self.resblocks.append(resblock(ch, k, d))
+
+        self.conv_post = Conv1d(ch, 1, 7, 1, padding=3, bias=False)
+        self.ups.apply(init_weights)
+
+        if gin_channels != 0:
+            self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1)
+
+    def forward(self, x: torch.Tensor, g: Optional[torch.Tensor] = None):
+        x = self.conv_pre(x)
+        if g is not None:
+            x = x + self.cond(g)
+
+        for i in range(self.num_upsamples):
+            x = F.leaky_relu(x, modules.LRELU_SLOPE)
+            x = self.ups[i](x)
+            xs = None
+            for j in range(self.num_kernels):
+                if xs is None:
+                    xs = self.resblocks[i * self.num_kernels + j](x)
+                else:
+                    xs += self.resblocks[i * self.num_kernels + j](x)
+            x = xs / self.num_kernels
+        x = F.leaky_relu(x)
+        x = self.conv_post(x)
+        x = torch.tanh(x)
+
+        return x
+
+    def __prepare_scriptable__(self):
+        for l in self.ups:
+            for hook in l._forward_pre_hooks.values():
+                # The hook we want to remove is an instance of WeightNorm class, so
+                # normally we would do `if isinstance(...)` but this class is not accessible
+                # because of shadowing, so we check the module name directly.
+                # https://github.com/pytorch/pytorch/blob/be0ca00c5ce260eb5bcec3237357f7a30cc08983/torch/nn/utils/__init__.py#L3
+                if (
+                    hook.__module__ == "torch.nn.utils.weight_norm"
+                    and hook.__class__.__name__ == "WeightNorm"
+                ):
+                    torch.nn.utils.remove_weight_norm(l)
+
+        for l in self.resblocks:
+            for hook in l._forward_pre_hooks.values():
+                if (
+                    hook.__module__ == "torch.nn.utils.weight_norm"
+                    and hook.__class__.__name__ == "WeightNorm"
+                ):
+                    torch.nn.utils.remove_weight_norm(l)
+        return self
+
+    def remove_weight_norm(self):
+        for l in self.ups:
+            remove_weight_norm(l)
+        for l in self.resblocks:
+            l.remove_weight_norm()
+
+
+class SineGen(torch.nn.Module):
+    """Definition of sine generator
+    SineGen(samp_rate, harmonic_num = 0,
+            sine_amp = 0.1, noise_std = 0.003,
+            voiced_threshold = 0,
+            flag_for_pulse=False)
+    samp_rate: sampling rate in Hz
+    harmonic_num: number of harmonic overtones (default 0)
+    sine_amp: amplitude of sine-wavefrom (default 0.1)
+    noise_std: std of Gaussian noise (default 0.003)
+    voiced_thoreshold: F0 threshold for U/V classification (default 0)
+    flag_for_pulse: this SinGen is used inside PulseGen (default False)
+    Note: when flag_for_pulse is True, the first time step of a voiced
+        segment is always sin(torch.pi) or cos(0)
+    """
+
+    def __init__(
+        self,
+        samp_rate,
+        harmonic_num=0,
+        sine_amp=0.1,
+        noise_std=0.003,
+        voiced_threshold=0,
+        flag_for_pulse=False,
+    ):
+        super(SineGen, self).__init__()
+        self.sine_amp = sine_amp
+        self.noise_std = noise_std
+        self.harmonic_num = harmonic_num
+        self.dim = self.harmonic_num + 1
+        self.sampling_rate = samp_rate
+        self.voiced_threshold = voiced_threshold
+
+    def _f02uv(self, f0):
+        # generate uv signal
+        uv = torch.ones_like(f0)
+        uv = uv * (f0 > self.voiced_threshold)
+        if uv.device.type == "privateuseone":  # for DirectML
+            uv = uv.float()
+        return uv
+
+    def forward(self, f0: torch.Tensor, upp: int):
+        """sine_tensor, uv = forward(f0)
+        input F0: tensor(batchsize=1, length, dim=1)
+                  f0 for unvoiced steps should be 0
+        output sine_tensor: tensor(batchsize=1, length, dim)
+        output uv: tensor(batchsize=1, length, 1)
+        """
+        with torch.no_grad():
+            device = next(self.parameters(), None)
+            if device is not None:
+                device = device.device
+            else:
+                device = f0.device
+            align_corners = device.type != "xpu"
+            f0 = f0[:, None].transpose(1, 2)
+            f0_buf = torch.zeros(f0.shape[0], f0.shape[1], self.dim, device=f0.device)
+            # fundamental component
+            f0_buf[:, :, 0] = f0[:, :, 0]
+            for idx in range(self.harmonic_num):
+                f0_buf[:, :, idx + 1] = f0_buf[:, :, 0] * (
+                    idx + 2
+                )  # idx + 2: the (idx+1)-th overtone, (idx+2)-th harmonic
+            rad_values = (f0_buf / self.sampling_rate) % 1  ###%1意味着n_har的乘积无法后处理优化
+            rand_ini = torch.rand(
+                f0_buf.shape[0], f0_buf.shape[2], device=f0_buf.device
+            )
+            rand_ini[:, 0] = 0
+            rad_values[:, 0, :] = rad_values[:, 0, :] + rand_ini
+            tmp_over_one = torch.cumsum(rad_values, 1)  # % 1  #####%1意味着后面的cumsum无法再优化
+            tmp_over_one *= upp
+            tmp_over_one = F.interpolate(
+                tmp_over_one.transpose(2, 1),
+                scale_factor=float(upp),
+                mode="linear",
+                align_corners=align_corners,
+            ).transpose(2, 1)
+            rad_values = F.interpolate(
+                rad_values.transpose(2, 1), scale_factor=float(upp), mode="nearest"
+            ).transpose(
+                2, 1
+            )  #######
+            tmp_over_one %= 1
+            tmp_over_one_idx = (tmp_over_one[:, 1:, :] - tmp_over_one[:, :-1, :]) < 0
+            cumsum_shift = torch.zeros_like(rad_values)
+            cumsum_shift[:, 1:, :] = tmp_over_one_idx * -1.0
+            sine_waves = torch.sin(
+                torch.cumsum(rad_values + cumsum_shift, dim=1) * 2 * torch.pi
+            )
+            sine_waves = sine_waves * self.sine_amp
+            uv = self._f02uv(f0)
+            uv = F.interpolate(
+                uv.transpose(2, 1), scale_factor=float(upp), mode="nearest"
+            ).transpose(2, 1)
+            noise_amp = uv * self.noise_std + (1 - uv) * self.sine_amp / 3
+            noise = noise_amp * torch.randn_like(sine_waves)
+            sine_waves = sine_waves * uv + noise
+        return sine_waves, uv, noise
+
+
+class SourceModuleHnNSF(torch.nn.Module):
+    """SourceModule for hn-nsf
+    SourceModule(sampling_rate, harmonic_num=0, sine_amp=0.1,
+                 add_noise_std=0.003, voiced_threshod=0)
+    sampling_rate: sampling_rate in Hz
+    harmonic_num: number of harmonic above F0 (default: 0)
+    sine_amp: amplitude of sine source signal (default: 0.1)
+    add_noise_std: std of additive Gaussian noise (default: 0.003)
+        note that amplitude of noise in unvoiced is decided
+        by sine_amp
+    voiced_threshold: threhold to set U/V given F0 (default: 0)
+    Sine_source, noise_source = SourceModuleHnNSF(F0_sampled)
+    F0_sampled (batchsize, length, 1)
+    Sine_source (batchsize, length, 1)
+    noise_source (batchsize, length 1)
+    uv (batchsize, length, 1)
+    """
+
+    def __init__(
+        self,
+        sampling_rate,
+        harmonic_num=0,
+        sine_amp=0.1,
+        add_noise_std=0.003,
+        voiced_threshod=0,
+        is_half=True,
+    ):
+        super(SourceModuleHnNSF, self).__init__()
+
+        self.sine_amp = sine_amp
+        self.noise_std = add_noise_std
+        self.is_half = is_half
+        # to produce sine waveforms
+        self.l_sin_gen = SineGen(
+            sampling_rate, harmonic_num, sine_amp, add_noise_std, voiced_threshod
+        )
+
+        # to merge source harmonics into a single excitation
+        self.l_linear = torch.nn.Linear(harmonic_num + 1, 1)
+        self.l_tanh = torch.nn.Tanh()
+        # self.ddtype:int = -1
+
+    def forward(self, x: torch.Tensor, upp: int = 1):
+        # if self.ddtype ==-1:
+        #     self.ddtype = self.l_linear.weight.dtype
+        sine_wavs, uv, _ = self.l_sin_gen(x, upp)
+        # print(x.dtype,sine_wavs.dtype,self.l_linear.weight.dtype)
+        # if self.is_half:
+        #     sine_wavs = sine_wavs.half()
+        # sine_merge = self.l_tanh(self.l_linear(sine_wavs.to(x)))
+        # print(sine_wavs.dtype,self.ddtype)
+        # if sine_wavs.dtype != self.l_linear.weight.dtype:
+        sine_wavs = sine_wavs.to(dtype=self.l_linear.weight.dtype)
+        sine_merge = self.l_tanh(self.l_linear(sine_wavs))
+        return sine_merge, None, None  # noise, uv
+
+
+class GeneratorNSF(torch.nn.Module):
+    def __init__(
+        self,
+        initial_channel,
+        resblock,
+        resblock_kernel_sizes,
+        resblock_dilation_sizes,
+        upsample_rates,
+        upsample_initial_channel,
+        upsample_kernel_sizes,
+        gin_channels,
+        sr,
+        is_half=False,
+    ):
+        super(GeneratorNSF, self).__init__()
+        self.num_kernels = len(resblock_kernel_sizes)
+        self.num_upsamples = len(upsample_rates)
+
+        self.f0_upsamp = torch.nn.Upsample(scale_factor=math.prod(upsample_rates))
+        self.m_source = SourceModuleHnNSF(
+            sampling_rate=sr, harmonic_num=0, is_half=is_half
+        )
+        self.noise_convs = nn.ModuleList()
+        self.conv_pre = Conv1d(
+            initial_channel, upsample_initial_channel, 7, 1, padding=3
+        )
+        resblock = modules.ResBlock1 if resblock == "1" else modules.ResBlock2
+
+        self.ups = nn.ModuleList()
+        for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
+            c_cur = upsample_initial_channel // (2 ** (i + 1))
+            self.ups.append(
+                weight_norm(
+                    ConvTranspose1d(
+                        upsample_initial_channel // (2**i),
+                        upsample_initial_channel // (2 ** (i + 1)),
+                        k,
+                        u,
+                        padding=(k - u) // 2,
+                    )
+                )
+            )
+            if i + 1 < len(upsample_rates):
+                stride_f0 = math.prod(upsample_rates[i + 1 :])
+                self.noise_convs.append(
+                    Conv1d(
+                        1,
+                        c_cur,
+                        kernel_size=stride_f0 * 2,
+                        stride=stride_f0,
+                        padding=stride_f0 // 2,
+                    )
+                )
+            else:
+                self.noise_convs.append(Conv1d(1, c_cur, kernel_size=1))
+
+        self.resblocks = nn.ModuleList()
+        for i in range(len(self.ups)):
+            ch = upsample_initial_channel // (2 ** (i + 1))
+            for j, (k, d) in enumerate(
+                zip(resblock_kernel_sizes, resblock_dilation_sizes)
+            ):
+                self.resblocks.append(resblock(ch, k, d))
+
+        self.conv_post = Conv1d(ch, 1, 7, 1, padding=3, bias=False)
+        self.ups.apply(init_weights)
+
+        if gin_channels != 0:
+            self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1)
+
+        self.upp = math.prod(upsample_rates)
+
+        self.lrelu_slope = modules.LRELU_SLOPE
+
+    def forward(self, x, f0, g: Optional[torch.Tensor] = None):
+        har_source, noi_source, uv = self.m_source(f0, self.upp)
+        har_source = har_source.transpose(1, 2)
+        x = self.conv_pre(x)
+        if g is not None:
+            x = x + self.cond(g)
+        # torch.jit.script() does not support direct indexing of torch modules
+        # That's why I wrote this
+        for i, (ups, noise_convs) in enumerate(zip(self.ups, self.noise_convs)):
+            if i < self.num_upsamples:
+                x = F.leaky_relu(x, self.lrelu_slope)
+                x = ups(x)
+                x_source = noise_convs(har_source)
+                x = x + x_source
+                xs: Optional[torch.Tensor] = None
+                l = [i * self.num_kernels + j for j in range(self.num_kernels)]
+                for j, resblock in enumerate(self.resblocks):
+                    if j in l:
+                        if xs is None:
+                            xs = resblock(x)
+                        else:
+                            xs += resblock(x)
+                # This assertion cannot be ignored! \
+                # If ignored, it will cause torch.jit.script() compilation errors
+                assert isinstance(xs, torch.Tensor)
+                x = xs / self.num_kernels
+        x = F.leaky_relu(x)
+        x = self.conv_post(x)
+        x = torch.tanh(x)
+        return x
+
+    def remove_weight_norm(self):
+        for l in self.ups:
+            remove_weight_norm(l)
+        for l in self.resblocks:
+            l.remove_weight_norm()
+
+    def __prepare_scriptable__(self):
+        for l in self.ups:
+            for hook in l._forward_pre_hooks.values():
+                # The hook we want to remove is an instance of WeightNorm class, so
+                # normally we would do `if isinstance(...)` but this class is not accessible
+                # because of shadowing, so we check the module name directly.
+                # https://github.com/pytorch/pytorch/blob/be0ca00c5ce260eb5bcec3237357f7a30cc08983/torch/nn/utils/__init__.py#L3
+                if (
+                    hook.__module__ == "torch.nn.utils.weight_norm"
+                    and hook.__class__.__name__ == "WeightNorm"
+                ):
+                    torch.nn.utils.remove_weight_norm(l)
+        for l in self.resblocks:
+            for hook in self.resblocks._forward_pre_hooks.values():
+                if (
+                    hook.__module__ == "torch.nn.utils.weight_norm"
+                    and hook.__class__.__name__ == "WeightNorm"
+                ):
+                    torch.nn.utils.remove_weight_norm(l)
+        return self
+
+
+sr2sr = {
+    "32k": 32000,
+    "40k": 40000,
+    "48k": 48000,
+}
+
+
+class SynthesizerTrnMs256NSFsid(nn.Module):
+    def __init__(
+        self,
+        spec_channels,
+        segment_size,
+        inter_channels,
+        hidden_channels,
+        filter_channels,
+        n_heads,
+        n_layers,
+        kernel_size,
+        p_dropout,
+        resblock,
+        resblock_kernel_sizes,
+        resblock_dilation_sizes,
+        upsample_rates,
+        upsample_initial_channel,
+        upsample_kernel_sizes,
+        spk_embed_dim,
+        gin_channels,
+        sr,
+        **kwargs
+    ):
+        super(SynthesizerTrnMs256NSFsid, self).__init__()
+        if isinstance(sr, str):
+            sr = sr2sr[sr]
+        self.spec_channels = spec_channels
+        self.inter_channels = inter_channels
+        self.hidden_channels = hidden_channels
+        self.filter_channels = filter_channels
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.kernel_size = kernel_size
+        self.p_dropout = float(p_dropout)
+        self.resblock = resblock
+        self.resblock_kernel_sizes = resblock_kernel_sizes
+        self.resblock_dilation_sizes = resblock_dilation_sizes
+        self.upsample_rates = upsample_rates
+        self.upsample_initial_channel = upsample_initial_channel
+        self.upsample_kernel_sizes = upsample_kernel_sizes
+        self.segment_size = segment_size
+        self.gin_channels = gin_channels
+        # self.hop_length = hop_length#
+        self.spk_embed_dim = spk_embed_dim
+        self.enc_p = TextEncoder256(
+            inter_channels,
+            hidden_channels,
+            filter_channels,
+            n_heads,
+            n_layers,
+            kernel_size,
+            float(p_dropout),
+        )
+        self.dec = GeneratorNSF(
+            inter_channels,
+            resblock,
+            resblock_kernel_sizes,
+            resblock_dilation_sizes,
+            upsample_rates,
+            upsample_initial_channel,
+            upsample_kernel_sizes,
+            gin_channels=gin_channels,
+            sr=sr,
+            is_half=kwargs["is_half"],
+        )
+        self.enc_q = PosteriorEncoder(
+            spec_channels,
+            inter_channels,
+            hidden_channels,
+            5,
+            1,
+            16,
+            gin_channels=gin_channels,
+        )
+        self.flow = ResidualCouplingBlock(
+            inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
+        )
+        self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
+        logger.debug(
+            "gin_channels: "
+            + str(gin_channels)
+            + ", self.spk_embed_dim: "
+            + str(self.spk_embed_dim)
+        )
+
+    def remove_weight_norm(self):
+        self.dec.remove_weight_norm()
+        self.flow.remove_weight_norm()
+        self.enc_q.remove_weight_norm()
+
+    def __prepare_scriptable__(self):
+        for hook in self.dec._forward_pre_hooks.values():
+            # The hook we want to remove is an instance of WeightNorm class, so
+            # normally we would do `if isinstance(...)` but this class is not accessible
+            # because of shadowing, so we check the module name directly.
+            # https://github.com/pytorch/pytorch/blob/be0ca00c5ce260eb5bcec3237357f7a30cc08983/torch/nn/utils/__init__.py#L3
+            if (
+                hook.__module__ == "torch.nn.utils.weight_norm"
+                and hook.__class__.__name__ == "WeightNorm"
+            ):
+                torch.nn.utils.remove_weight_norm(self.dec)
+        for hook in self.flow._forward_pre_hooks.values():
+            if (
+                hook.__module__ == "torch.nn.utils.weight_norm"
+                and hook.__class__.__name__ == "WeightNorm"
+            ):
+                torch.nn.utils.remove_weight_norm(self.flow)
+        if hasattr(self, "enc_q"):
+            for hook in self.enc_q._forward_pre_hooks.values():
+                if (
+                    hook.__module__ == "torch.nn.utils.weight_norm"
+                    and hook.__class__.__name__ == "WeightNorm"
+                ):
+                    torch.nn.utils.remove_weight_norm(self.enc_q)
+        return self
+
+    @torch.jit.ignore
+    def forward(
+        self,
+        phone: torch.Tensor,
+        phone_lengths: torch.Tensor,
+        pitch: torch.Tensor,
+        pitchf: torch.Tensor,
+        y: torch.Tensor,
+        y_lengths: torch.Tensor,
+        ds: Optional[torch.Tensor] = None,
+    ):  # 这里ds是id，[bs,1]
+        # print(1,pitch.shape)#[bs,t]
+        g = self.emb_g(ds).unsqueeze(-1)  # [b, 256, 1]##1是t，广播的
+        m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
+        z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
+        z_p = self.flow(z, y_mask, g=g)
+        z_slice, ids_slice = commons.rand_slice_segments(
+            z, y_lengths, self.segment_size
+        )
+        # print(-1,pitchf.shape,ids_slice,self.segment_size,self.hop_length,self.segment_size//self.hop_length)
+        pitchf = commons.slice_segments2(pitchf, ids_slice, self.segment_size)
+        # print(-2,pitchf.shape,z_slice.shape)
+        o = self.dec(z_slice, pitchf, g=g)
+        return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
+
+    @torch.jit.export
+    def infer(
+        self,
+        phone: torch.Tensor,
+        phone_lengths: torch.Tensor,
+        pitch: torch.Tensor,
+        nsff0: torch.Tensor,
+        sid: torch.Tensor,
+        rate: Optional[torch.Tensor] = None,
+    ):
+        g = self.emb_g(sid).unsqueeze(-1)
+        m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
+        z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
+        if rate is not None:
+            assert isinstance(rate, torch.Tensor)
+            head = int(z_p.shape[2] * (1 - rate.item()))
+            z_p = z_p[:, :, head:]
+            x_mask = x_mask[:, :, head:]
+            nsff0 = nsff0[:, head:]
+        z = self.flow(z_p, x_mask, g=g, reverse=True)
+        o = self.dec(z * x_mask, nsff0, g=g)
+        return o, x_mask, (z, z_p, m_p, logs_p)
+
+
+class SynthesizerTrnMs768NSFsid(nn.Module):
+    def __init__(
+        self,
+        spec_channels,
+        segment_size,
+        inter_channels,
+        hidden_channels,
+        filter_channels,
+        n_heads,
+        n_layers,
+        kernel_size,
+        p_dropout,
+        resblock,
+        resblock_kernel_sizes,
+        resblock_dilation_sizes,
+        upsample_rates,
+        upsample_initial_channel,
+        upsample_kernel_sizes,
+        spk_embed_dim,
+        gin_channels,
+        sr,
+        **kwargs
+    ):
+        super(SynthesizerTrnMs768NSFsid, self).__init__()
+        if isinstance(sr, str):
+            sr = sr2sr[sr]
+        self.spec_channels = spec_channels
+        self.inter_channels = inter_channels
+        self.hidden_channels = hidden_channels
+        self.filter_channels = filter_channels
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.kernel_size = kernel_size
+        self.p_dropout = float(p_dropout)
+        self.resblock = resblock
+        self.resblock_kernel_sizes = resblock_kernel_sizes
+        self.resblock_dilation_sizes = resblock_dilation_sizes
+        self.upsample_rates = upsample_rates
+        self.upsample_initial_channel = upsample_initial_channel
+        self.upsample_kernel_sizes = upsample_kernel_sizes
+        self.segment_size = segment_size
+        self.gin_channels = gin_channels
+        # self.hop_length = hop_length#
+        self.spk_embed_dim = spk_embed_dim
+        self.enc_p = TextEncoder768(
+            inter_channels,
+            hidden_channels,
+            filter_channels,
+            n_heads,
+            n_layers,
+            kernel_size,
+            float(p_dropout),
+        )
+        self.dec = GeneratorNSF(
+            inter_channels,
+            resblock,
+            resblock_kernel_sizes,
+            resblock_dilation_sizes,
+            upsample_rates,
+            upsample_initial_channel,
+            upsample_kernel_sizes,
+            gin_channels=gin_channels,
+            sr=sr,
+            is_half=kwargs["is_half"],
+        )
+        self.enc_q = PosteriorEncoder(
+            spec_channels,
+            inter_channels,
+            hidden_channels,
+            5,
+            1,
+            16,
+            gin_channels=gin_channels,
+        )
+        self.flow = ResidualCouplingBlock(
+            inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
+        )
+        self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
+        logger.debug(
+            "gin_channels: "
+            + str(gin_channels)
+            + ", self.spk_embed_dim: "
+            + str(self.spk_embed_dim)
+        )
+
+    def remove_weight_norm(self):
+        self.dec.remove_weight_norm()
+        self.flow.remove_weight_norm()
+        self.enc_q.remove_weight_norm()
+
+    def __prepare_scriptable__(self):
+        for hook in self.dec._forward_pre_hooks.values():
+            # The hook we want to remove is an instance of WeightNorm class, so
+            # normally we would do `if isinstance(...)` but this class is not accessible
+            # because of shadowing, so we check the module name directly.
+            # https://github.com/pytorch/pytorch/blob/be0ca00c5ce260eb5bcec3237357f7a30cc08983/torch/nn/utils/__init__.py#L3
+            if (
+                hook.__module__ == "torch.nn.utils.weight_norm"
+                and hook.__class__.__name__ == "WeightNorm"
+            ):
+                torch.nn.utils.remove_weight_norm(self.dec)
+        for hook in self.flow._forward_pre_hooks.values():
+            if (
+                hook.__module__ == "torch.nn.utils.weight_norm"
+                and hook.__class__.__name__ == "WeightNorm"
+            ):
+                torch.nn.utils.remove_weight_norm(self.flow)
+        if hasattr(self, "enc_q"):
+            for hook in self.enc_q._forward_pre_hooks.values():
+                if (
+                    hook.__module__ == "torch.nn.utils.weight_norm"
+                    and hook.__class__.__name__ == "WeightNorm"
+                ):
+                    torch.nn.utils.remove_weight_norm(self.enc_q)
+        return self
+
+    @torch.jit.ignore
+    def forward(
+        self, phone, phone_lengths, pitch, pitchf, y, y_lengths, ds
+    ):  # 这里ds是id，[bs,1]
+        # print(1,pitch.shape)#[bs,t]
+        g = self.emb_g(ds).unsqueeze(-1)  # [b, 256, 1]##1是t，广播的
+        m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
+        z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
+        z_p = self.flow(z, y_mask, g=g)
+        z_slice, ids_slice = commons.rand_slice_segments(
+            z, y_lengths, self.segment_size
+        )
+        # print(-1,pitchf.shape,ids_slice,self.segment_size,self.hop_length,self.segment_size//self.hop_length)
+        pitchf = commons.slice_segments2(pitchf, ids_slice, self.segment_size)
+        # print(-2,pitchf.shape,z_slice.shape)
+        o = self.dec(z_slice, pitchf, g=g)
+        return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
+
+    @torch.jit.export
+    def infer(
+        self,
+        phone: torch.Tensor,
+        phone_lengths: torch.Tensor,
+        pitch: torch.Tensor,
+        nsff0: torch.Tensor,
+        sid: torch.Tensor,
+        rate: Optional[torch.Tensor] = None,
+    ):
+        g = self.emb_g(sid).unsqueeze(-1)
+        m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
+        z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
+        if rate is not None:
+            head = int(z_p.shape[2] * (1.0 - rate.item()))
+            z_p = z_p[:, :, head:]
+            x_mask = x_mask[:, :, head:]
+            nsff0 = nsff0[:, head:]
+        z = self.flow(z_p, x_mask, g=g, reverse=True)
+        o = self.dec(z * x_mask, nsff0, g=g)
+        return o, x_mask, (z, z_p, m_p, logs_p)
+
+
+class SynthesizerTrnMs256NSFsid_nono(nn.Module):
+    def __init__(
+        self,
+        spec_channels,
+        segment_size,
+        inter_channels,
+        hidden_channels,
+        filter_channels,
+        n_heads,
+        n_layers,
+        kernel_size,
+        p_dropout,
+        resblock,
+        resblock_kernel_sizes,
+        resblock_dilation_sizes,
+        upsample_rates,
+        upsample_initial_channel,
+        upsample_kernel_sizes,
+        spk_embed_dim,
+        gin_channels,
+        sr=None,
+        **kwargs
+    ):
+        super(SynthesizerTrnMs256NSFsid_nono, self).__init__()
+        self.spec_channels = spec_channels
+        self.inter_channels = inter_channels
+        self.hidden_channels = hidden_channels
+        self.filter_channels = filter_channels
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.kernel_size = kernel_size
+        self.p_dropout = float(p_dropout)
+        self.resblock = resblock
+        self.resblock_kernel_sizes = resblock_kernel_sizes
+        self.resblock_dilation_sizes = resblock_dilation_sizes
+        self.upsample_rates = upsample_rates
+        self.upsample_initial_channel = upsample_initial_channel
+        self.upsample_kernel_sizes = upsample_kernel_sizes
+        self.segment_size = segment_size
+        self.gin_channels = gin_channels
+        # self.hop_length = hop_length#
+        self.spk_embed_dim = spk_embed_dim
+        self.enc_p = TextEncoder256(
+            inter_channels,
+            hidden_channels,
+            filter_channels,
+            n_heads,
+            n_layers,
+            kernel_size,
+            float(p_dropout),
+            f0=False,
+        )
+        self.dec = Generator(
+            inter_channels,
+            resblock,
+            resblock_kernel_sizes,
+            resblock_dilation_sizes,
+            upsample_rates,
+            upsample_initial_channel,
+            upsample_kernel_sizes,
+            gin_channels=gin_channels,
+        )
+        self.enc_q = PosteriorEncoder(
+            spec_channels,
+            inter_channels,
+            hidden_channels,
+            5,
+            1,
+            16,
+            gin_channels=gin_channels,
+        )
+        self.flow = ResidualCouplingBlock(
+            inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
+        )
+        self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
+        logger.debug(
+            "gin_channels: "
+            + str(gin_channels)
+            + ", self.spk_embed_dim: "
+            + str(self.spk_embed_dim)
+        )
+
+    def remove_weight_norm(self):
+        self.dec.remove_weight_norm()
+        self.flow.remove_weight_norm()
+        self.enc_q.remove_weight_norm()
+
+    def __prepare_scriptable__(self):
+        for hook in self.dec._forward_pre_hooks.values():
+            # The hook we want to remove is an instance of WeightNorm class, so
+            # normally we would do `if isinstance(...)` but this class is not accessible
+            # because of shadowing, so we check the module name directly.
+            # https://github.com/pytorch/pytorch/blob/be0ca00c5ce260eb5bcec3237357f7a30cc08983/torch/nn/utils/__init__.py#L3
+            if (
+                hook.__module__ == "torch.nn.utils.weight_norm"
+                and hook.__class__.__name__ == "WeightNorm"
+            ):
+                torch.nn.utils.remove_weight_norm(self.dec)
+        for hook in self.flow._forward_pre_hooks.values():
+            if (
+                hook.__module__ == "torch.nn.utils.weight_norm"
+                and hook.__class__.__name__ == "WeightNorm"
+            ):
+                torch.nn.utils.remove_weight_norm(self.flow)
+        if hasattr(self, "enc_q"):
+            for hook in self.enc_q._forward_pre_hooks.values():
+                if (
+                    hook.__module__ == "torch.nn.utils.weight_norm"
+                    and hook.__class__.__name__ == "WeightNorm"
+                ):
+                    torch.nn.utils.remove_weight_norm(self.enc_q)
+        return self
+
+    @torch.jit.ignore
+    def forward(self, phone, phone_lengths, y, y_lengths, ds):  # 这里ds是id，[bs,1]
+        g = self.emb_g(ds).unsqueeze(-1)  # [b, 256, 1]##1是t，广播的
+        m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
+        z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
+        z_p = self.flow(z, y_mask, g=g)
+        z_slice, ids_slice = commons.rand_slice_segments(
+            z, y_lengths, self.segment_size
+        )
+        o = self.dec(z_slice, g=g)
+        return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
+
+    @torch.jit.export
+    def infer(
+        self,
+        phone: torch.Tensor,
+        phone_lengths: torch.Tensor,
+        sid: torch.Tensor,
+        rate: Optional[torch.Tensor] = None,
+    ):
+        g = self.emb_g(sid).unsqueeze(-1)
+        m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
+        z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
+        if rate is not None:
+            head = int(z_p.shape[2] * (1.0 - rate.item()))
+            z_p = z_p[:, :, head:]
+            x_mask = x_mask[:, :, head:]
+        z = self.flow(z_p, x_mask, g=g, reverse=True)
+        o = self.dec(z * x_mask, g=g)
+        return o, x_mask, (z, z_p, m_p, logs_p)
+
+
+class SynthesizerTrnMs768NSFsid_nono(nn.Module):
+    def __init__(
+        self,
+        spec_channels,
+        segment_size,
+        inter_channels,
+        hidden_channels,
+        filter_channels,
+        n_heads,
+        n_layers,
+        kernel_size,
+        p_dropout,
+        resblock,
+        resblock_kernel_sizes,
+        resblock_dilation_sizes,
+        upsample_rates,
+        upsample_initial_channel,
+        upsample_kernel_sizes,
+        spk_embed_dim,
+        gin_channels,
+        sr=None,
+        **kwargs
+    ):
+        super(SynthesizerTrnMs768NSFsid_nono, self).__init__()
+        self.spec_channels = spec_channels
+        self.inter_channels = inter_channels
+        self.hidden_channels = hidden_channels
+        self.filter_channels = filter_channels
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.kernel_size = kernel_size
+        self.p_dropout = float(p_dropout)
+        self.resblock = resblock
+        self.resblock_kernel_sizes = resblock_kernel_sizes
+        self.resblock_dilation_sizes = resblock_dilation_sizes
+        self.upsample_rates = upsample_rates
+        self.upsample_initial_channel = upsample_initial_channel
+        self.upsample_kernel_sizes = upsample_kernel_sizes
+        self.segment_size = segment_size
+        self.gin_channels = gin_channels
+        # self.hop_length = hop_length#
+        self.spk_embed_dim = spk_embed_dim
+        self.enc_p = TextEncoder768(
+            inter_channels,
+            hidden_channels,
+            filter_channels,
+            n_heads,
+            n_layers,
+            kernel_size,
+            float(p_dropout),
+            f0=False,
+        )
+        self.dec = Generator(
+            inter_channels,
+            resblock,
+            resblock_kernel_sizes,
+            resblock_dilation_sizes,
+            upsample_rates,
+            upsample_initial_channel,
+            upsample_kernel_sizes,
+            gin_channels=gin_channels,
+        )
+        self.enc_q = PosteriorEncoder(
+            spec_channels,
+            inter_channels,
+            hidden_channels,
+            5,
+            1,
+            16,
+            gin_channels=gin_channels,
+        )
+        self.flow = ResidualCouplingBlock(
+            inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
+        )
+        self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
+        logger.debug(
+            "gin_channels: "
+            + str(gin_channels)
+            + ", self.spk_embed_dim: "
+            + str(self.spk_embed_dim)
+        )
+
+    def remove_weight_norm(self):
+        self.dec.remove_weight_norm()
+        self.flow.remove_weight_norm()
+        self.enc_q.remove_weight_norm()
+
+    def __prepare_scriptable__(self):
+        for hook in self.dec._forward_pre_hooks.values():
+            # The hook we want to remove is an instance of WeightNorm class, so
+            # normally we would do `if isinstance(...)` but this class is not accessible
+            # because of shadowing, so we check the module name directly.
+            # https://github.com/pytorch/pytorch/blob/be0ca00c5ce260eb5bcec3237357f7a30cc08983/torch/nn/utils/__init__.py#L3
+            if (
+                hook.__module__ == "torch.nn.utils.weight_norm"
+                and hook.__class__.__name__ == "WeightNorm"
+            ):
+                torch.nn.utils.remove_weight_norm(self.dec)
+        for hook in self.flow._forward_pre_hooks.values():
+            if (
+                hook.__module__ == "torch.nn.utils.weight_norm"
+                and hook.__class__.__name__ == "WeightNorm"
+            ):
+                torch.nn.utils.remove_weight_norm(self.flow)
+        if hasattr(self, "enc_q"):
+            for hook in self.enc_q._forward_pre_hooks.values():
+                if (
+                    hook.__module__ == "torch.nn.utils.weight_norm"
+                    and hook.__class__.__name__ == "WeightNorm"
+                ):
+                    torch.nn.utils.remove_weight_norm(self.enc_q)
+        return self
+
+    @torch.jit.ignore
+    def forward(self, phone, phone_lengths, y, y_lengths, ds):  # 这里ds是id，[bs,1]
+        g = self.emb_g(ds).unsqueeze(-1)  # [b, 256, 1]##1是t，广播的
+        m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
+        z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
+        z_p = self.flow(z, y_mask, g=g)
+        z_slice, ids_slice = commons.rand_slice_segments(
+            z, y_lengths, self.segment_size
+        )
+        o = self.dec(z_slice, g=g)
+        return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
+
+    @torch.jit.export
+    def infer(
+        self,
+        phone: torch.Tensor,
+        phone_lengths: torch.Tensor,
+        sid: torch.Tensor,
+        rate: Optional[torch.Tensor] = None,
+    ):
+        g = self.emb_g(sid).unsqueeze(-1)
+        m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
+        z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
+        if rate is not None:
+            head = int(z_p.shape[2] * (1.0 - rate.item()))
+            z_p = z_p[:, :, head:]
+            x_mask = x_mask[:, :, head:]
+        z = self.flow(z_p, x_mask, g=g, reverse=True)
+        o = self.dec(z * x_mask, g=g)
+        return o, x_mask, (z, z_p, m_p, logs_p)
+
+
+class MultiPeriodDiscriminator(torch.nn.Module):
+    def __init__(self, use_spectral_norm=False):
+        super(MultiPeriodDiscriminator, self).__init__()
+        periods = [2, 3, 5, 7, 11, 17]
+        # periods = [3, 5, 7, 11, 17, 23, 37]
+
+        discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)]
+        discs = discs + [
+            DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods
+        ]
+        self.discriminators = nn.ModuleList(discs)
+
+    def forward(self, y, y_hat):
+        y_d_rs = []  #
+        y_d_gs = []
+        fmap_rs = []
+        fmap_gs = []
+        for i, d in enumerate(self.discriminators):
+            y_d_r, fmap_r = d(y)
+            y_d_g, fmap_g = d(y_hat)
+            # for j in range(len(fmap_r)):
+            #     print(i,j,y.shape,y_hat.shape,fmap_r[j].shape,fmap_g[j].shape)
+            y_d_rs.append(y_d_r)
+            y_d_gs.append(y_d_g)
+            fmap_rs.append(fmap_r)
+            fmap_gs.append(fmap_g)
+
+        return y_d_rs, y_d_gs, fmap_rs, fmap_gs
+
+
+class MultiPeriodDiscriminatorV2(torch.nn.Module):
+    def __init__(self, use_spectral_norm=False):
+        super(MultiPeriodDiscriminatorV2, self).__init__()
+        # periods = [2, 3, 5, 7, 11, 17]
+        periods = [2, 3, 5, 7, 11, 17, 23, 37]
+
+        discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)]
+        discs = discs + [
+            DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods
+        ]
+        self.discriminators = nn.ModuleList(discs)
+
+    def forward(self, y, y_hat):
+        y_d_rs = []  #
+        y_d_gs = []
+        fmap_rs = []
+        fmap_gs = []
+        for i, d in enumerate(self.discriminators):
+            y_d_r, fmap_r = d(y)
+            y_d_g, fmap_g = d(y_hat)
+            # for j in range(len(fmap_r)):
+            #     print(i,j,y.shape,y_hat.shape,fmap_r[j].shape,fmap_g[j].shape)
+            y_d_rs.append(y_d_r)
+            y_d_gs.append(y_d_g)
+            fmap_rs.append(fmap_r)
+            fmap_gs.append(fmap_g)
+
+        return y_d_rs, y_d_gs, fmap_rs, fmap_gs
+
+
+class DiscriminatorS(torch.nn.Module):
+    def __init__(self, use_spectral_norm=False):
+        super(DiscriminatorS, self).__init__()
+        norm_f = weight_norm if use_spectral_norm == False else spectral_norm
+        self.convs = nn.ModuleList(
+            [
+                norm_f(Conv1d(1, 16, 15, 1, padding=7)),
+                norm_f(Conv1d(16, 64, 41, 4, groups=4, padding=20)),
+                norm_f(Conv1d(64, 256, 41, 4, groups=16, padding=20)),
+                norm_f(Conv1d(256, 1024, 41, 4, groups=64, padding=20)),
+                norm_f(Conv1d(1024, 1024, 41, 4, groups=256, padding=20)),
+                norm_f(Conv1d(1024, 1024, 5, 1, padding=2)),
+            ]
+        )
+        self.conv_post = norm_f(Conv1d(1024, 1, 3, 1, padding=1))
+
+    def forward(self, x):
+        fmap = []
+
+        for l in self.convs:
+            x = l(x)
+            x = F.leaky_relu(x, modules.LRELU_SLOPE)
+            fmap.append(x)
+        x = self.conv_post(x)
+        fmap.append(x)
+        x = torch.flatten(x, 1, -1)
+
+        return x, fmap
+
+
+class DiscriminatorP(torch.nn.Module):
+    def __init__(self, period, kernel_size=5, stride=3, use_spectral_norm=False):
+        super(DiscriminatorP, self).__init__()
+        self.period = period
+        self.use_spectral_norm = use_spectral_norm
+        norm_f = weight_norm if use_spectral_norm == False else spectral_norm
+        self.convs = nn.ModuleList(
+            [
+                norm_f(
+                    Conv2d(
+                        1,
+                        32,
+                        (kernel_size, 1),
+                        (stride, 1),
+                        padding=(get_padding(kernel_size, 1), 0),
+                    )
+                ),
+                norm_f(
+                    Conv2d(
+                        32,
+                        128,
+                        (kernel_size, 1),
+                        (stride, 1),
+                        padding=(get_padding(kernel_size, 1), 0),
+                    )
+                ),
+                norm_f(
+                    Conv2d(
+                        128,
+                        512,
+                        (kernel_size, 1),
+                        (stride, 1),
+                        padding=(get_padding(kernel_size, 1), 0),
+                    )
+                ),
+                norm_f(
+                    Conv2d(
+                        512,
+                        1024,
+                        (kernel_size, 1),
+                        (stride, 1),
+                        padding=(get_padding(kernel_size, 1), 0),
+                    )
+                ),
+                norm_f(
+                    Conv2d(
+                        1024,
+                        1024,
+                        (kernel_size, 1),
+                        1,
+                        padding=(get_padding(kernel_size, 1), 0),
+                    )
+                ),
+            ]
+        )
+        self.conv_post = norm_f(Conv2d(1024, 1, (3, 1), 1, padding=(1, 0)))
+
+    def forward(self, x):
+        fmap = []
+
+        # 1d to 2d
+        b, c, t = x.shape
+        if t % self.period != 0:  # pad first
+            n_pad = self.period - (t % self.period)
+            if has_xpu and x.dtype == torch.bfloat16:
+                x = F.pad(x.to(dtype=torch.float16), (0, n_pad), "reflect").to(
+                    dtype=torch.bfloat16
+                )
+            else:
+                x = F.pad(x, (0, n_pad), "reflect")
+            t = t + n_pad
+        x = x.view(b, c, t // self.period, self.period)
+
+        for l in self.convs:
+            x = l(x)
+            x = F.leaky_relu(x, modules.LRELU_SLOPE)
+            fmap.append(x)
+        x = self.conv_post(x)
+        fmap.append(x)
+        x = torch.flatten(x, 1, -1)
+
+        return x, fmap
diff --git a/rvc/lib/infer_pack/models_onnx.py b/rvc/lib/infer_pack/models_onnx.py
new file mode 100644
index 0000000000000000000000000000000000000000..81a533c449b2ef9827d70a250ae8ddee696d3488
--- /dev/null
+++ b/rvc/lib/infer_pack/models_onnx.py
@@ -0,0 +1,821 @@
+import logging
+import math
+
+logger = logging.getLogger(__name__)
+
+import numpy as np
+import torch
+from torch import nn
+from torch.nn import AvgPool1d, Conv1d, Conv2d, ConvTranspose1d
+from torch.nn import functional as F
+from torch.nn.utils import remove_weight_norm, spectral_norm, weight_norm
+
+from rvc.lib.infer_pack import attentions, commons, modules
+from rvc.lib.infer_pack.commons import get_padding, init_weights
+
+
+class TextEncoder256(nn.Module):
+    def __init__(
+        self,
+        out_channels,
+        hidden_channels,
+        filter_channels,
+        n_heads,
+        n_layers,
+        kernel_size,
+        p_dropout,
+        f0=True,
+    ):
+        super().__init__()
+        self.out_channels = out_channels
+        self.hidden_channels = hidden_channels
+        self.filter_channels = filter_channels
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.kernel_size = kernel_size
+        self.p_dropout = p_dropout
+        self.emb_phone = nn.Linear(256, hidden_channels)
+        self.lrelu = nn.LeakyReLU(0.1, inplace=True)
+        if f0 == True:
+            self.emb_pitch = nn.Embedding(256, hidden_channels)  # pitch 256
+        self.encoder = attentions.Encoder(
+            hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout
+        )
+        self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
+
+    def forward(self, phone, pitch, lengths):
+        if pitch == None:
+            x = self.emb_phone(phone)
+        else:
+            x = self.emb_phone(phone) + self.emb_pitch(pitch)
+        x = x * math.sqrt(self.hidden_channels)  # [b, t, h]
+        x = self.lrelu(x)
+        x = torch.transpose(x, 1, -1)  # [b, h, t]
+        x_mask = torch.unsqueeze(commons.sequence_mask(lengths, x.size(2)), 1).to(
+            x.dtype
+        )
+        x = self.encoder(x * x_mask, x_mask)
+        stats = self.proj(x) * x_mask
+
+        m, logs = torch.split(stats, self.out_channels, dim=1)
+        return m, logs, x_mask
+
+
+class TextEncoder768(nn.Module):
+    def __init__(
+        self,
+        out_channels,
+        hidden_channels,
+        filter_channels,
+        n_heads,
+        n_layers,
+        kernel_size,
+        p_dropout,
+        f0=True,
+    ):
+        super().__init__()
+        self.out_channels = out_channels
+        self.hidden_channels = hidden_channels
+        self.filter_channels = filter_channels
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.kernel_size = kernel_size
+        self.p_dropout = p_dropout
+        self.emb_phone = nn.Linear(768, hidden_channels)
+        self.lrelu = nn.LeakyReLU(0.1, inplace=True)
+        if f0 == True:
+            self.emb_pitch = nn.Embedding(256, hidden_channels)  # pitch 256
+        self.encoder = attentions.Encoder(
+            hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout
+        )
+        self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
+
+    def forward(self, phone, pitch, lengths):
+        if pitch == None:
+            x = self.emb_phone(phone)
+        else:
+            x = self.emb_phone(phone) + self.emb_pitch(pitch)
+        x = x * math.sqrt(self.hidden_channels)  # [b, t, h]
+        x = self.lrelu(x)
+        x = torch.transpose(x, 1, -1)  # [b, h, t]
+        x_mask = torch.unsqueeze(commons.sequence_mask(lengths, x.size(2)), 1).to(
+            x.dtype
+        )
+        x = self.encoder(x * x_mask, x_mask)
+        stats = self.proj(x) * x_mask
+
+        m, logs = torch.split(stats, self.out_channels, dim=1)
+        return m, logs, x_mask
+
+
+class ResidualCouplingBlock(nn.Module):
+    def __init__(
+        self,
+        channels,
+        hidden_channels,
+        kernel_size,
+        dilation_rate,
+        n_layers,
+        n_flows=4,
+        gin_channels=0,
+    ):
+        super().__init__()
+        self.channels = channels
+        self.hidden_channels = hidden_channels
+        self.kernel_size = kernel_size
+        self.dilation_rate = dilation_rate
+        self.n_layers = n_layers
+        self.n_flows = n_flows
+        self.gin_channels = gin_channels
+
+        self.flows = nn.ModuleList()
+        for i in range(n_flows):
+            self.flows.append(
+                modules.ResidualCouplingLayer(
+                    channels,
+                    hidden_channels,
+                    kernel_size,
+                    dilation_rate,
+                    n_layers,
+                    gin_channels=gin_channels,
+                    mean_only=True,
+                )
+            )
+            self.flows.append(modules.Flip())
+
+    def forward(self, x, x_mask, g=None, reverse=False):
+        if not reverse:
+            for flow in self.flows:
+                x, _ = flow(x, x_mask, g=g, reverse=reverse)
+        else:
+            for flow in reversed(self.flows):
+                x, _ = flow(x, x_mask, g=g, reverse=reverse)
+        return x
+
+    def remove_weight_norm(self):
+        for i in range(self.n_flows):
+            self.flows[i * 2].remove_weight_norm()
+
+
+class PosteriorEncoder(nn.Module):
+    def __init__(
+        self,
+        in_channels,
+        out_channels,
+        hidden_channels,
+        kernel_size,
+        dilation_rate,
+        n_layers,
+        gin_channels=0,
+    ):
+        super().__init__()
+        self.in_channels = in_channels
+        self.out_channels = out_channels
+        self.hidden_channels = hidden_channels
+        self.kernel_size = kernel_size
+        self.dilation_rate = dilation_rate
+        self.n_layers = n_layers
+        self.gin_channels = gin_channels
+
+        self.pre = nn.Conv1d(in_channels, hidden_channels, 1)
+        self.enc = modules.WN(
+            hidden_channels,
+            kernel_size,
+            dilation_rate,
+            n_layers,
+            gin_channels=gin_channels,
+        )
+        self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
+
+    def forward(self, x, x_lengths, g=None):
+        x_mask = torch.unsqueeze(commons.sequence_mask(x_lengths, x.size(2)), 1).to(
+            x.dtype
+        )
+        x = self.pre(x) * x_mask
+        x = self.enc(x, x_mask, g=g)
+        stats = self.proj(x) * x_mask
+        m, logs = torch.split(stats, self.out_channels, dim=1)
+        z = (m + torch.randn_like(m) * torch.exp(logs)) * x_mask
+        return z, m, logs, x_mask
+
+    def remove_weight_norm(self):
+        self.enc.remove_weight_norm()
+
+
+class Generator(torch.nn.Module):
+    def __init__(
+        self,
+        initial_channel,
+        resblock,
+        resblock_kernel_sizes,
+        resblock_dilation_sizes,
+        upsample_rates,
+        upsample_initial_channel,
+        upsample_kernel_sizes,
+        gin_channels=0,
+    ):
+        super(Generator, self).__init__()
+        self.num_kernels = len(resblock_kernel_sizes)
+        self.num_upsamples = len(upsample_rates)
+        self.conv_pre = Conv1d(
+            initial_channel, upsample_initial_channel, 7, 1, padding=3
+        )
+        resblock = modules.ResBlock1 if resblock == "1" else modules.ResBlock2
+
+        self.ups = nn.ModuleList()
+        for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
+            self.ups.append(
+                weight_norm(
+                    ConvTranspose1d(
+                        upsample_initial_channel // (2**i),
+                        upsample_initial_channel // (2 ** (i + 1)),
+                        k,
+                        u,
+                        padding=(k - u) // 2,
+                    )
+                )
+            )
+
+        self.resblocks = nn.ModuleList()
+        for i in range(len(self.ups)):
+            ch = upsample_initial_channel // (2 ** (i + 1))
+            for j, (k, d) in enumerate(
+                zip(resblock_kernel_sizes, resblock_dilation_sizes)
+            ):
+                self.resblocks.append(resblock(ch, k, d))
+
+        self.conv_post = Conv1d(ch, 1, 7, 1, padding=3, bias=False)
+        self.ups.apply(init_weights)
+
+        if gin_channels != 0:
+            self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1)
+
+    def forward(self, x, g=None):
+        x = self.conv_pre(x)
+        if g is not None:
+            x = x + self.cond(g)
+
+        for i in range(self.num_upsamples):
+            x = F.leaky_relu(x, modules.LRELU_SLOPE)
+            x = self.ups[i](x)
+            xs = None
+            for j in range(self.num_kernels):
+                if xs is None:
+                    xs = self.resblocks[i * self.num_kernels + j](x)
+                else:
+                    xs += self.resblocks[i * self.num_kernels + j](x)
+            x = xs / self.num_kernels
+        x = F.leaky_relu(x)
+        x = self.conv_post(x)
+        x = torch.tanh(x)
+
+        return x
+
+    def remove_weight_norm(self):
+        for l in self.ups:
+            remove_weight_norm(l)
+        for l in self.resblocks:
+            l.remove_weight_norm()
+
+
+class SineGen(torch.nn.Module):
+    """Definition of sine generator
+    SineGen(samp_rate, harmonic_num = 0,
+            sine_amp = 0.1, noise_std = 0.003,
+            voiced_threshold = 0,
+            flag_for_pulse=False)
+    samp_rate: sampling rate in Hz
+    harmonic_num: number of harmonic overtones (default 0)
+    sine_amp: amplitude of sine-wavefrom (default 0.1)
+    noise_std: std of Gaussian noise (default 0.003)
+    voiced_thoreshold: F0 threshold for U/V classification (default 0)
+    flag_for_pulse: this SinGen is used inside PulseGen (default False)
+    Note: when flag_for_pulse is True, the first time step of a voiced
+        segment is always sin(np.pi) or cos(0)
+    """
+
+    def __init__(
+        self,
+        samp_rate,
+        harmonic_num=0,
+        sine_amp=0.1,
+        noise_std=0.003,
+        voiced_threshold=0,
+        flag_for_pulse=False,
+    ):
+        super(SineGen, self).__init__()
+        self.sine_amp = sine_amp
+        self.noise_std = noise_std
+        self.harmonic_num = harmonic_num
+        self.dim = self.harmonic_num + 1
+        self.sampling_rate = samp_rate
+        self.voiced_threshold = voiced_threshold
+
+    def _f02uv(self, f0):
+        # generate uv signal
+        uv = torch.ones_like(f0)
+        uv = uv * (f0 > self.voiced_threshold)
+        return uv
+
+    def forward(self, f0, upp):
+        """sine_tensor, uv = forward(f0)
+        input F0: tensor(batchsize=1, length, dim=1)
+                  f0 for unvoiced steps should be 0
+        output sine_tensor: tensor(batchsize=1, length, dim)
+        output uv: tensor(batchsize=1, length, 1)
+        """
+        with torch.no_grad():
+            f0 = f0[:, None].transpose(1, 2)
+            f0_buf = torch.zeros(f0.shape[0], f0.shape[1], self.dim, device=f0.device)
+            # fundamental component
+            f0_buf[:, :, 0] = f0[:, :, 0]
+            for idx in np.arange(self.harmonic_num):
+                f0_buf[:, :, idx + 1] = f0_buf[:, :, 0] * (
+                    idx + 2
+                )  # idx + 2: the (idx+1)-th overtone, (idx+2)-th harmonic
+            rad_values = (f0_buf / self.sampling_rate) % 1  ###%1意味着n_har的乘积无法后处理优化
+            rand_ini = torch.rand(
+                f0_buf.shape[0], f0_buf.shape[2], device=f0_buf.device
+            )
+            rand_ini[:, 0] = 0
+            rad_values[:, 0, :] = rad_values[:, 0, :] + rand_ini
+            tmp_over_one = torch.cumsum(rad_values, 1)  # % 1  #####%1意味着后面的cumsum无法再优化
+            tmp_over_one *= upp
+            tmp_over_one = F.interpolate(
+                tmp_over_one.transpose(2, 1),
+                scale_factor=upp,
+                mode="linear",
+                align_corners=True,
+            ).transpose(2, 1)
+            rad_values = F.interpolate(
+                rad_values.transpose(2, 1), scale_factor=upp, mode="nearest"
+            ).transpose(
+                2, 1
+            )  #######
+            tmp_over_one %= 1
+            tmp_over_one_idx = (tmp_over_one[:, 1:, :] - tmp_over_one[:, :-1, :]) < 0
+            cumsum_shift = torch.zeros_like(rad_values)
+            cumsum_shift[:, 1:, :] = tmp_over_one_idx * -1.0
+            sine_waves = torch.sin(
+                torch.cumsum(rad_values + cumsum_shift, dim=1) * 2 * np.pi
+            )
+            sine_waves = sine_waves * self.sine_amp
+            uv = self._f02uv(f0)
+            uv = F.interpolate(
+                uv.transpose(2, 1), scale_factor=upp, mode="nearest"
+            ).transpose(2, 1)
+            noise_amp = uv * self.noise_std + (1 - uv) * self.sine_amp / 3
+            noise = noise_amp * torch.randn_like(sine_waves)
+            sine_waves = sine_waves * uv + noise
+        return sine_waves, uv, noise
+
+
+class SourceModuleHnNSF(torch.nn.Module):
+    """SourceModule for hn-nsf
+    SourceModule(sampling_rate, harmonic_num=0, sine_amp=0.1,
+                 add_noise_std=0.003, voiced_threshod=0)
+    sampling_rate: sampling_rate in Hz
+    harmonic_num: number of harmonic above F0 (default: 0)
+    sine_amp: amplitude of sine source signal (default: 0.1)
+    add_noise_std: std of additive Gaussian noise (default: 0.003)
+        note that amplitude of noise in unvoiced is decided
+        by sine_amp
+    voiced_threshold: threhold to set U/V given F0 (default: 0)
+    Sine_source, noise_source = SourceModuleHnNSF(F0_sampled)
+    F0_sampled (batchsize, length, 1)
+    Sine_source (batchsize, length, 1)
+    noise_source (batchsize, length 1)
+    uv (batchsize, length, 1)
+    """
+
+    def __init__(
+        self,
+        sampling_rate,
+        harmonic_num=0,
+        sine_amp=0.1,
+        add_noise_std=0.003,
+        voiced_threshod=0,
+        is_half=True,
+    ):
+        super(SourceModuleHnNSF, self).__init__()
+
+        self.sine_amp = sine_amp
+        self.noise_std = add_noise_std
+        self.is_half = is_half
+        # to produce sine waveforms
+        self.l_sin_gen = SineGen(
+            sampling_rate, harmonic_num, sine_amp, add_noise_std, voiced_threshod
+        )
+
+        # to merge source harmonics into a single excitation
+        self.l_linear = torch.nn.Linear(harmonic_num + 1, 1)
+        self.l_tanh = torch.nn.Tanh()
+
+    def forward(self, x, upp=None):
+        sine_wavs, uv, _ = self.l_sin_gen(x, upp)
+        if self.is_half:
+            sine_wavs = sine_wavs.half()
+        sine_merge = self.l_tanh(self.l_linear(sine_wavs))
+        return sine_merge, None, None  # noise, uv
+
+
+class GeneratorNSF(torch.nn.Module):
+    def __init__(
+        self,
+        initial_channel,
+        resblock,
+        resblock_kernel_sizes,
+        resblock_dilation_sizes,
+        upsample_rates,
+        upsample_initial_channel,
+        upsample_kernel_sizes,
+        gin_channels,
+        sr,
+        is_half=False,
+    ):
+        super(GeneratorNSF, self).__init__()
+        self.num_kernels = len(resblock_kernel_sizes)
+        self.num_upsamples = len(upsample_rates)
+
+        self.f0_upsamp = torch.nn.Upsample(scale_factor=np.prod(upsample_rates))
+        self.m_source = SourceModuleHnNSF(
+            sampling_rate=sr, harmonic_num=0, is_half=is_half
+        )
+        self.noise_convs = nn.ModuleList()
+        self.conv_pre = Conv1d(
+            initial_channel, upsample_initial_channel, 7, 1, padding=3
+        )
+        resblock = modules.ResBlock1 if resblock == "1" else modules.ResBlock2
+
+        self.ups = nn.ModuleList()
+        for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
+            c_cur = upsample_initial_channel // (2 ** (i + 1))
+            self.ups.append(
+                weight_norm(
+                    ConvTranspose1d(
+                        upsample_initial_channel // (2**i),
+                        upsample_initial_channel // (2 ** (i + 1)),
+                        k,
+                        u,
+                        padding=(k - u) // 2,
+                    )
+                )
+            )
+            if i + 1 < len(upsample_rates):
+                stride_f0 = np.prod(upsample_rates[i + 1 :])
+                self.noise_convs.append(
+                    Conv1d(
+                        1,
+                        c_cur,
+                        kernel_size=stride_f0 * 2,
+                        stride=stride_f0,
+                        padding=stride_f0 // 2,
+                    )
+                )
+            else:
+                self.noise_convs.append(Conv1d(1, c_cur, kernel_size=1))
+
+        self.resblocks = nn.ModuleList()
+        for i in range(len(self.ups)):
+            ch = upsample_initial_channel // (2 ** (i + 1))
+            for j, (k, d) in enumerate(
+                zip(resblock_kernel_sizes, resblock_dilation_sizes)
+            ):
+                self.resblocks.append(resblock(ch, k, d))
+
+        self.conv_post = Conv1d(ch, 1, 7, 1, padding=3, bias=False)
+        self.ups.apply(init_weights)
+
+        if gin_channels != 0:
+            self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1)
+
+        self.upp = np.prod(upsample_rates)
+
+    def forward(self, x, f0, g=None):
+        har_source, noi_source, uv = self.m_source(f0, self.upp)
+        har_source = har_source.transpose(1, 2)
+        x = self.conv_pre(x)
+        if g is not None:
+            x = x + self.cond(g)
+
+        for i in range(self.num_upsamples):
+            x = F.leaky_relu(x, modules.LRELU_SLOPE)
+            x = self.ups[i](x)
+            x_source = self.noise_convs[i](har_source)
+            x = x + x_source
+            xs = None
+            for j in range(self.num_kernels):
+                if xs is None:
+                    xs = self.resblocks[i * self.num_kernels + j](x)
+                else:
+                    xs += self.resblocks[i * self.num_kernels + j](x)
+            x = xs / self.num_kernels
+        x = F.leaky_relu(x)
+        x = self.conv_post(x)
+        x = torch.tanh(x)
+        return x
+
+    def remove_weight_norm(self):
+        for l in self.ups:
+            remove_weight_norm(l)
+        for l in self.resblocks:
+            l.remove_weight_norm()
+
+
+sr2sr = {
+    "32k": 32000,
+    "40k": 40000,
+    "48k": 48000,
+}
+
+
+class SynthesizerTrnMsNSFsidM(nn.Module):
+    def __init__(
+        self,
+        spec_channels,
+        segment_size,
+        inter_channels,
+        hidden_channels,
+        filter_channels,
+        n_heads,
+        n_layers,
+        kernel_size,
+        p_dropout,
+        resblock,
+        resblock_kernel_sizes,
+        resblock_dilation_sizes,
+        upsample_rates,
+        upsample_initial_channel,
+        upsample_kernel_sizes,
+        spk_embed_dim,
+        gin_channels,
+        sr,
+        version,
+        **kwargs,
+    ):
+        super().__init__()
+        if type(sr) == type("strr"):
+            sr = sr2sr[sr]
+        self.spec_channels = spec_channels
+        self.inter_channels = inter_channels
+        self.hidden_channels = hidden_channels
+        self.filter_channels = filter_channels
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.kernel_size = kernel_size
+        self.p_dropout = p_dropout
+        self.resblock = resblock
+        self.resblock_kernel_sizes = resblock_kernel_sizes
+        self.resblock_dilation_sizes = resblock_dilation_sizes
+        self.upsample_rates = upsample_rates
+        self.upsample_initial_channel = upsample_initial_channel
+        self.upsample_kernel_sizes = upsample_kernel_sizes
+        self.segment_size = segment_size
+        self.gin_channels = gin_channels
+        # self.hop_length = hop_length#
+        self.spk_embed_dim = spk_embed_dim
+        if version == "v1":
+            self.enc_p = TextEncoder256(
+                inter_channels,
+                hidden_channels,
+                filter_channels,
+                n_heads,
+                n_layers,
+                kernel_size,
+                p_dropout,
+            )
+        else:
+            self.enc_p = TextEncoder768(
+                inter_channels,
+                hidden_channels,
+                filter_channels,
+                n_heads,
+                n_layers,
+                kernel_size,
+                p_dropout,
+            )
+        self.dec = GeneratorNSF(
+            inter_channels,
+            resblock,
+            resblock_kernel_sizes,
+            resblock_dilation_sizes,
+            upsample_rates,
+            upsample_initial_channel,
+            upsample_kernel_sizes,
+            gin_channels=gin_channels,
+            sr=sr,
+            is_half=kwargs["is_half"],
+        )
+        self.enc_q = PosteriorEncoder(
+            spec_channels,
+            inter_channels,
+            hidden_channels,
+            5,
+            1,
+            16,
+            gin_channels=gin_channels,
+        )
+        self.flow = ResidualCouplingBlock(
+            inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
+        )
+        self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
+        self.speaker_map = None
+        logger.debug(
+            f"gin_channels: {gin_channels}, self.spk_embed_dim: {self.spk_embed_dim}"
+        )
+
+    def remove_weight_norm(self):
+        self.dec.remove_weight_norm()
+        self.flow.remove_weight_norm()
+        self.enc_q.remove_weight_norm()
+
+    def construct_spkmixmap(self, n_speaker):
+        self.speaker_map = torch.zeros((n_speaker, 1, 1, self.gin_channels))
+        for i in range(n_speaker):
+            self.speaker_map[i] = self.emb_g(torch.LongTensor([[i]]))
+        self.speaker_map = self.speaker_map.unsqueeze(0)
+
+    def forward(self, phone, phone_lengths, pitch, nsff0, g, rnd, max_len=None):
+        if self.speaker_map is not None:  # [N, S]  *  [S, B, 1, H]
+            g = g.reshape((g.shape[0], g.shape[1], 1, 1, 1))  # [N, S, B, 1, 1]
+            g = g * self.speaker_map  # [N, S, B, 1, H]
+            g = torch.sum(g, dim=1)  # [N, 1, B, 1, H]
+            g = g.transpose(0, -1).transpose(0, -2).squeeze(0)  # [B, H, N]
+        else:
+            g = g.unsqueeze(0)
+            g = self.emb_g(g).transpose(1, 2)
+
+        m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
+        z_p = (m_p + torch.exp(logs_p) * rnd) * x_mask
+        z = self.flow(z_p, x_mask, g=g, reverse=True)
+        o = self.dec((z * x_mask)[:, :, :max_len], nsff0, g=g)
+        return o
+
+
+class MultiPeriodDiscriminator(torch.nn.Module):
+    def __init__(self, use_spectral_norm=False):
+        super(MultiPeriodDiscriminator, self).__init__()
+        periods = [2, 3, 5, 7, 11, 17]
+        # periods = [3, 5, 7, 11, 17, 23, 37]
+
+        discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)]
+        discs = discs + [
+            DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods
+        ]
+        self.discriminators = nn.ModuleList(discs)
+
+    def forward(self, y, y_hat):
+        y_d_rs = []  #
+        y_d_gs = []
+        fmap_rs = []
+        fmap_gs = []
+        for i, d in enumerate(self.discriminators):
+            y_d_r, fmap_r = d(y)
+            y_d_g, fmap_g = d(y_hat)
+            # for j in range(len(fmap_r)):
+            #     print(i,j,y.shape,y_hat.shape,fmap_r[j].shape,fmap_g[j].shape)
+            y_d_rs.append(y_d_r)
+            y_d_gs.append(y_d_g)
+            fmap_rs.append(fmap_r)
+            fmap_gs.append(fmap_g)
+
+        return y_d_rs, y_d_gs, fmap_rs, fmap_gs
+
+
+class MultiPeriodDiscriminatorV2(torch.nn.Module):
+    def __init__(self, use_spectral_norm=False):
+        super(MultiPeriodDiscriminatorV2, self).__init__()
+        # periods = [2, 3, 5, 7, 11, 17]
+        periods = [2, 3, 5, 7, 11, 17, 23, 37]
+
+        discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)]
+        discs = discs + [
+            DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods
+        ]
+        self.discriminators = nn.ModuleList(discs)
+
+    def forward(self, y, y_hat):
+        y_d_rs = []  #
+        y_d_gs = []
+        fmap_rs = []
+        fmap_gs = []
+        for i, d in enumerate(self.discriminators):
+            y_d_r, fmap_r = d(y)
+            y_d_g, fmap_g = d(y_hat)
+            # for j in range(len(fmap_r)):
+            #     print(i,j,y.shape,y_hat.shape,fmap_r[j].shape,fmap_g[j].shape)
+            y_d_rs.append(y_d_r)
+            y_d_gs.append(y_d_g)
+            fmap_rs.append(fmap_r)
+            fmap_gs.append(fmap_g)
+
+        return y_d_rs, y_d_gs, fmap_rs, fmap_gs
+
+
+class DiscriminatorS(torch.nn.Module):
+    def __init__(self, use_spectral_norm=False):
+        super(DiscriminatorS, self).__init__()
+        norm_f = weight_norm if use_spectral_norm == False else spectral_norm
+        self.convs = nn.ModuleList(
+            [
+                norm_f(Conv1d(1, 16, 15, 1, padding=7)),
+                norm_f(Conv1d(16, 64, 41, 4, groups=4, padding=20)),
+                norm_f(Conv1d(64, 256, 41, 4, groups=16, padding=20)),
+                norm_f(Conv1d(256, 1024, 41, 4, groups=64, padding=20)),
+                norm_f(Conv1d(1024, 1024, 41, 4, groups=256, padding=20)),
+                norm_f(Conv1d(1024, 1024, 5, 1, padding=2)),
+            ]
+        )
+        self.conv_post = norm_f(Conv1d(1024, 1, 3, 1, padding=1))
+
+    def forward(self, x):
+        fmap = []
+
+        for l in self.convs:
+            x = l(x)
+            x = F.leaky_relu(x, modules.LRELU_SLOPE)
+            fmap.append(x)
+        x = self.conv_post(x)
+        fmap.append(x)
+        x = torch.flatten(x, 1, -1)
+
+        return x, fmap
+
+
+class DiscriminatorP(torch.nn.Module):
+    def __init__(self, period, kernel_size=5, stride=3, use_spectral_norm=False):
+        super(DiscriminatorP, self).__init__()
+        self.period = period
+        self.use_spectral_norm = use_spectral_norm
+        norm_f = weight_norm if use_spectral_norm == False else spectral_norm
+        self.convs = nn.ModuleList(
+            [
+                norm_f(
+                    Conv2d(
+                        1,
+                        32,
+                        (kernel_size, 1),
+                        (stride, 1),
+                        padding=(get_padding(kernel_size, 1), 0),
+                    )
+                ),
+                norm_f(
+                    Conv2d(
+                        32,
+                        128,
+                        (kernel_size, 1),
+                        (stride, 1),
+                        padding=(get_padding(kernel_size, 1), 0),
+                    )
+                ),
+                norm_f(
+                    Conv2d(
+                        128,
+                        512,
+                        (kernel_size, 1),
+                        (stride, 1),
+                        padding=(get_padding(kernel_size, 1), 0),
+                    )
+                ),
+                norm_f(
+                    Conv2d(
+                        512,
+                        1024,
+                        (kernel_size, 1),
+                        (stride, 1),
+                        padding=(get_padding(kernel_size, 1), 0),
+                    )
+                ),
+                norm_f(
+                    Conv2d(
+                        1024,
+                        1024,
+                        (kernel_size, 1),
+                        1,
+                        padding=(get_padding(kernel_size, 1), 0),
+                    )
+                ),
+            ]
+        )
+        self.conv_post = norm_f(Conv2d(1024, 1, (3, 1), 1, padding=(1, 0)))
+
+    def forward(self, x):
+        fmap = []
+
+        # 1d to 2d
+        b, c, t = x.shape
+        if t % self.period != 0:  # pad first
+            n_pad = self.period - (t % self.period)
+            x = F.pad(x, (0, n_pad), "reflect")
+            t = t + n_pad
+        x = x.view(b, c, t // self.period, self.period)
+
+        for l in self.convs:
+            x = l(x)
+            x = F.leaky_relu(x, modules.LRELU_SLOPE)
+            fmap.append(x)
+        x = self.conv_post(x)
+        fmap.append(x)
+        x = torch.flatten(x, 1, -1)
+
+        return x, fmap
diff --git a/rvc/lib/infer_pack/modules.py b/rvc/lib/infer_pack/modules.py
new file mode 100644
index 0000000000000000000000000000000000000000..aa0a12000ffa94c26cd12b0add1d677f930bdf13
--- /dev/null
+++ b/rvc/lib/infer_pack/modules.py
@@ -0,0 +1,615 @@
+import copy
+import math
+from typing import Optional, Tuple
+
+import numpy as np
+import scipy
+import torch
+from torch import nn
+from torch.nn import AvgPool1d, Conv1d, Conv2d, ConvTranspose1d
+from torch.nn import functional as F
+from torch.nn.utils import remove_weight_norm, weight_norm
+
+from rvc.lib.infer_pack import commons
+from rvc.lib.infer_pack.commons import get_padding, init_weights
+from rvc.lib.infer_pack.transforms import piecewise_rational_quadratic_transform
+
+LRELU_SLOPE = 0.1
+
+
+class LayerNorm(nn.Module):
+    def __init__(self, channels, eps=1e-5):
+        super(LayerNorm, self).__init__()
+        self.channels = channels
+        self.eps = eps
+
+        self.gamma = nn.Parameter(torch.ones(channels))
+        self.beta = nn.Parameter(torch.zeros(channels))
+
+    def forward(self, x):
+        x = x.transpose(1, -1)
+        x = F.layer_norm(x, (self.channels,), self.gamma, self.beta, self.eps)
+        return x.transpose(1, -1)
+
+
+class ConvReluNorm(nn.Module):
+    def __init__(
+        self,
+        in_channels,
+        hidden_channels,
+        out_channels,
+        kernel_size,
+        n_layers,
+        p_dropout,
+    ):
+        super(ConvReluNorm, self).__init__()
+        self.in_channels = in_channels
+        self.hidden_channels = hidden_channels
+        self.out_channels = out_channels
+        self.kernel_size = kernel_size
+        self.n_layers = n_layers
+        self.p_dropout = float(p_dropout)
+        assert n_layers > 1, "Number of layers should be larger than 0."
+
+        self.conv_layers = nn.ModuleList()
+        self.norm_layers = nn.ModuleList()
+        self.conv_layers.append(
+            nn.Conv1d(
+                in_channels, hidden_channels, kernel_size, padding=kernel_size // 2
+            )
+        )
+        self.norm_layers.append(LayerNorm(hidden_channels))
+        self.relu_drop = nn.Sequential(nn.ReLU(), nn.Dropout(float(p_dropout)))
+        for _ in range(n_layers - 1):
+            self.conv_layers.append(
+                nn.Conv1d(
+                    hidden_channels,
+                    hidden_channels,
+                    kernel_size,
+                    padding=kernel_size // 2,
+                )
+            )
+            self.norm_layers.append(LayerNorm(hidden_channels))
+        self.proj = nn.Conv1d(hidden_channels, out_channels, 1)
+        self.proj.weight.data.zero_()
+        self.proj.bias.data.zero_()
+
+    def forward(self, x, x_mask):
+        x_org = x
+        for i in range(self.n_layers):
+            x = self.conv_layers[i](x * x_mask)
+            x = self.norm_layers[i](x)
+            x = self.relu_drop(x)
+        x = x_org + self.proj(x)
+        return x * x_mask
+
+
+class DDSConv(nn.Module):
+    """
+    Dialted and Depth-Separable Convolution
+    """
+
+    def __init__(self, channels, kernel_size, n_layers, p_dropout=0.0):
+        super(DDSConv, self).__init__()
+        self.channels = channels
+        self.kernel_size = kernel_size
+        self.n_layers = n_layers
+        self.p_dropout = float(p_dropout)
+
+        self.drop = nn.Dropout(float(p_dropout))
+        self.convs_sep = nn.ModuleList()
+        self.convs_1x1 = nn.ModuleList()
+        self.norms_1 = nn.ModuleList()
+        self.norms_2 = nn.ModuleList()
+        for i in range(n_layers):
+            dilation = kernel_size**i
+            padding = (kernel_size * dilation - dilation) // 2
+            self.convs_sep.append(
+                nn.Conv1d(
+                    channels,
+                    channels,
+                    kernel_size,
+                    groups=channels,
+                    dilation=dilation,
+                    padding=padding,
+                )
+            )
+            self.convs_1x1.append(nn.Conv1d(channels, channels, 1))
+            self.norms_1.append(LayerNorm(channels))
+            self.norms_2.append(LayerNorm(channels))
+
+    def forward(self, x, x_mask, g: Optional[torch.Tensor] = None):
+        if g is not None:
+            x = x + g
+        for i in range(self.n_layers):
+            y = self.convs_sep[i](x * x_mask)
+            y = self.norms_1[i](y)
+            y = F.gelu(y)
+            y = self.convs_1x1[i](y)
+            y = self.norms_2[i](y)
+            y = F.gelu(y)
+            y = self.drop(y)
+            x = x + y
+        return x * x_mask
+
+
+class WN(torch.nn.Module):
+    def __init__(
+        self,
+        hidden_channels,
+        kernel_size,
+        dilation_rate,
+        n_layers,
+        gin_channels=0,
+        p_dropout=0,
+    ):
+        super(WN, self).__init__()
+        assert kernel_size % 2 == 1
+        self.hidden_channels = hidden_channels
+        self.kernel_size = (kernel_size,)
+        self.dilation_rate = dilation_rate
+        self.n_layers = n_layers
+        self.gin_channels = gin_channels
+        self.p_dropout = float(p_dropout)
+
+        self.in_layers = torch.nn.ModuleList()
+        self.res_skip_layers = torch.nn.ModuleList()
+        self.drop = nn.Dropout(float(p_dropout))
+
+        if gin_channels != 0:
+            cond_layer = torch.nn.Conv1d(
+                gin_channels, 2 * hidden_channels * n_layers, 1
+            )
+            self.cond_layer = torch.nn.utils.weight_norm(cond_layer, name="weight")
+
+        for i in range(n_layers):
+            dilation = dilation_rate**i
+            padding = int((kernel_size * dilation - dilation) / 2)
+            in_layer = torch.nn.Conv1d(
+                hidden_channels,
+                2 * hidden_channels,
+                kernel_size,
+                dilation=dilation,
+                padding=padding,
+            )
+            in_layer = torch.nn.utils.weight_norm(in_layer, name="weight")
+            self.in_layers.append(in_layer)
+
+            # last one is not necessary
+            if i < n_layers - 1:
+                res_skip_channels = 2 * hidden_channels
+            else:
+                res_skip_channels = hidden_channels
+
+            res_skip_layer = torch.nn.Conv1d(hidden_channels, res_skip_channels, 1)
+            res_skip_layer = torch.nn.utils.weight_norm(res_skip_layer, name="weight")
+            self.res_skip_layers.append(res_skip_layer)
+
+    def forward(
+        self, x: torch.Tensor, x_mask: torch.Tensor, g: Optional[torch.Tensor] = None
+    ):
+        output = torch.zeros_like(x)
+        n_channels_tensor = torch.IntTensor([self.hidden_channels])
+
+        if g is not None:
+            g = self.cond_layer(g)
+
+        for i, (in_layer, res_skip_layer) in enumerate(
+            zip(self.in_layers, self.res_skip_layers)
+        ):
+            x_in = in_layer(x)
+            if g is not None:
+                cond_offset = i * 2 * self.hidden_channels
+                g_l = g[:, cond_offset : cond_offset + 2 * self.hidden_channels, :]
+            else:
+                g_l = torch.zeros_like(x_in)
+
+            acts = commons.fused_add_tanh_sigmoid_multiply(x_in, g_l, n_channels_tensor)
+            acts = self.drop(acts)
+
+            res_skip_acts = res_skip_layer(acts)
+            if i < self.n_layers - 1:
+                res_acts = res_skip_acts[:, : self.hidden_channels, :]
+                x = (x + res_acts) * x_mask
+                output = output + res_skip_acts[:, self.hidden_channels :, :]
+            else:
+                output = output + res_skip_acts
+        return output * x_mask
+
+    def remove_weight_norm(self):
+        if self.gin_channels != 0:
+            torch.nn.utils.remove_weight_norm(self.cond_layer)
+        for l in self.in_layers:
+            torch.nn.utils.remove_weight_norm(l)
+        for l in self.res_skip_layers:
+            torch.nn.utils.remove_weight_norm(l)
+
+    def __prepare_scriptable__(self):
+        if self.gin_channels != 0:
+            for hook in self.cond_layer._forward_pre_hooks.values():
+                if (
+                    hook.__module__ == "torch.nn.utils.weight_norm"
+                    and hook.__class__.__name__ == "WeightNorm"
+                ):
+                    torch.nn.utils.remove_weight_norm(self.cond_layer)
+        for l in self.in_layers:
+            for hook in l._forward_pre_hooks.values():
+                if (
+                    hook.__module__ == "torch.nn.utils.weight_norm"
+                    and hook.__class__.__name__ == "WeightNorm"
+                ):
+                    torch.nn.utils.remove_weight_norm(l)
+        for l in self.res_skip_layers:
+            for hook in l._forward_pre_hooks.values():
+                if (
+                    hook.__module__ == "torch.nn.utils.weight_norm"
+                    and hook.__class__.__name__ == "WeightNorm"
+                ):
+                    torch.nn.utils.remove_weight_norm(l)
+        return self
+
+
+class ResBlock1(torch.nn.Module):
+    def __init__(self, channels, kernel_size=3, dilation=(1, 3, 5)):
+        super(ResBlock1, self).__init__()
+        self.convs1 = nn.ModuleList(
+            [
+                weight_norm(
+                    Conv1d(
+                        channels,
+                        channels,
+                        kernel_size,
+                        1,
+                        dilation=dilation[0],
+                        padding=get_padding(kernel_size, dilation[0]),
+                    )
+                ),
+                weight_norm(
+                    Conv1d(
+                        channels,
+                        channels,
+                        kernel_size,
+                        1,
+                        dilation=dilation[1],
+                        padding=get_padding(kernel_size, dilation[1]),
+                    )
+                ),
+                weight_norm(
+                    Conv1d(
+                        channels,
+                        channels,
+                        kernel_size,
+                        1,
+                        dilation=dilation[2],
+                        padding=get_padding(kernel_size, dilation[2]),
+                    )
+                ),
+            ]
+        )
+        self.convs1.apply(init_weights)
+
+        self.convs2 = nn.ModuleList(
+            [
+                weight_norm(
+                    Conv1d(
+                        channels,
+                        channels,
+                        kernel_size,
+                        1,
+                        dilation=1,
+                        padding=get_padding(kernel_size, 1),
+                    )
+                ),
+                weight_norm(
+                    Conv1d(
+                        channels,
+                        channels,
+                        kernel_size,
+                        1,
+                        dilation=1,
+                        padding=get_padding(kernel_size, 1),
+                    )
+                ),
+                weight_norm(
+                    Conv1d(
+                        channels,
+                        channels,
+                        kernel_size,
+                        1,
+                        dilation=1,
+                        padding=get_padding(kernel_size, 1),
+                    )
+                ),
+            ]
+        )
+        self.convs2.apply(init_weights)
+        self.lrelu_slope = LRELU_SLOPE
+
+    def forward(self, x: torch.Tensor, x_mask: Optional[torch.Tensor] = None):
+        for c1, c2 in zip(self.convs1, self.convs2):
+            xt = F.leaky_relu(x, self.lrelu_slope)
+            if x_mask is not None:
+                xt = xt * x_mask
+            xt = c1(xt)
+            xt = F.leaky_relu(xt, self.lrelu_slope)
+            if x_mask is not None:
+                xt = xt * x_mask
+            xt = c2(xt)
+            x = xt + x
+        if x_mask is not None:
+            x = x * x_mask
+        return x
+
+    def remove_weight_norm(self):
+        for l in self.convs1:
+            remove_weight_norm(l)
+        for l in self.convs2:
+            remove_weight_norm(l)
+
+    def __prepare_scriptable__(self):
+        for l in self.convs1:
+            for hook in l._forward_pre_hooks.values():
+                if (
+                    hook.__module__ == "torch.nn.utils.weight_norm"
+                    and hook.__class__.__name__ == "WeightNorm"
+                ):
+                    torch.nn.utils.remove_weight_norm(l)
+        for l in self.convs2:
+            for hook in l._forward_pre_hooks.values():
+                if (
+                    hook.__module__ == "torch.nn.utils.weight_norm"
+                    and hook.__class__.__name__ == "WeightNorm"
+                ):
+                    torch.nn.utils.remove_weight_norm(l)
+        return self
+
+
+class ResBlock2(torch.nn.Module):
+    def __init__(self, channels, kernel_size=3, dilation=(1, 3)):
+        super(ResBlock2, self).__init__()
+        self.convs = nn.ModuleList(
+            [
+                weight_norm(
+                    Conv1d(
+                        channels,
+                        channels,
+                        kernel_size,
+                        1,
+                        dilation=dilation[0],
+                        padding=get_padding(kernel_size, dilation[0]),
+                    )
+                ),
+                weight_norm(
+                    Conv1d(
+                        channels,
+                        channels,
+                        kernel_size,
+                        1,
+                        dilation=dilation[1],
+                        padding=get_padding(kernel_size, dilation[1]),
+                    )
+                ),
+            ]
+        )
+        self.convs.apply(init_weights)
+        self.lrelu_slope = LRELU_SLOPE
+
+    def forward(self, x, x_mask: Optional[torch.Tensor] = None):
+        for c in self.convs:
+            xt = F.leaky_relu(x, self.lrelu_slope)
+            if x_mask is not None:
+                xt = xt * x_mask
+            xt = c(xt)
+            x = xt + x
+        if x_mask is not None:
+            x = x * x_mask
+        return x
+
+    def remove_weight_norm(self):
+        for l in self.convs:
+            remove_weight_norm(l)
+
+    def __prepare_scriptable__(self):
+        for l in self.convs:
+            for hook in l._forward_pre_hooks.values():
+                if (
+                    hook.__module__ == "torch.nn.utils.weight_norm"
+                    and hook.__class__.__name__ == "WeightNorm"
+                ):
+                    torch.nn.utils.remove_weight_norm(l)
+        return self
+
+
+class Log(nn.Module):
+    def forward(
+        self,
+        x: torch.Tensor,
+        x_mask: torch.Tensor,
+        g: Optional[torch.Tensor] = None,
+        reverse: bool = False,
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
+        if not reverse:
+            y = torch.log(torch.clamp_min(x, 1e-5)) * x_mask
+            logdet = torch.sum(-y, [1, 2])
+            return y, logdet
+        else:
+            x = torch.exp(x) * x_mask
+            return x
+
+
+class Flip(nn.Module):
+    # torch.jit.script() Compiled functions \
+    # can't take variable number of arguments or \
+    # use keyword-only arguments with defaults
+    def forward(
+        self,
+        x: torch.Tensor,
+        x_mask: torch.Tensor,
+        g: Optional[torch.Tensor] = None,
+        reverse: bool = False,
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
+        x = torch.flip(x, [1])
+        if not reverse:
+            logdet = torch.zeros(x.size(0)).to(dtype=x.dtype, device=x.device)
+            return x, logdet
+        else:
+            return x, torch.zeros([1], device=x.device)
+
+
+class ElementwiseAffine(nn.Module):
+    def __init__(self, channels):
+        super(ElementwiseAffine, self).__init__()
+        self.channels = channels
+        self.m = nn.Parameter(torch.zeros(channels, 1))
+        self.logs = nn.Parameter(torch.zeros(channels, 1))
+
+    def forward(self, x, x_mask, reverse=False, **kwargs):
+        if not reverse:
+            y = self.m + torch.exp(self.logs) * x
+            y = y * x_mask
+            logdet = torch.sum(self.logs * x_mask, [1, 2])
+            return y, logdet
+        else:
+            x = (x - self.m) * torch.exp(-self.logs) * x_mask
+            return x
+
+
+class ResidualCouplingLayer(nn.Module):
+    def __init__(
+        self,
+        channels,
+        hidden_channels,
+        kernel_size,
+        dilation_rate,
+        n_layers,
+        p_dropout=0,
+        gin_channels=0,
+        mean_only=False,
+    ):
+        assert channels % 2 == 0, "channels should be divisible by 2"
+        super(ResidualCouplingLayer, self).__init__()
+        self.channels = channels
+        self.hidden_channels = hidden_channels
+        self.kernel_size = kernel_size
+        self.dilation_rate = dilation_rate
+        self.n_layers = n_layers
+        self.half_channels = channels // 2
+        self.mean_only = mean_only
+
+        self.pre = nn.Conv1d(self.half_channels, hidden_channels, 1)
+        self.enc = WN(
+            hidden_channels,
+            kernel_size,
+            dilation_rate,
+            n_layers,
+            p_dropout=float(p_dropout),
+            gin_channels=gin_channels,
+        )
+        self.post = nn.Conv1d(hidden_channels, self.half_channels * (2 - mean_only), 1)
+        self.post.weight.data.zero_()
+        self.post.bias.data.zero_()
+
+    def forward(
+        self,
+        x: torch.Tensor,
+        x_mask: torch.Tensor,
+        g: Optional[torch.Tensor] = None,
+        reverse: bool = False,
+    ):
+        x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
+        h = self.pre(x0) * x_mask
+        h = self.enc(h, x_mask, g=g)
+        stats = self.post(h) * x_mask
+        if not self.mean_only:
+            m, logs = torch.split(stats, [self.half_channels] * 2, 1)
+        else:
+            m = stats
+            logs = torch.zeros_like(m)
+
+        if not reverse:
+            x1 = m + x1 * torch.exp(logs) * x_mask
+            x = torch.cat([x0, x1], 1)
+            logdet = torch.sum(logs, [1, 2])
+            return x, logdet
+        else:
+            x1 = (x1 - m) * torch.exp(-logs) * x_mask
+            x = torch.cat([x0, x1], 1)
+            return x, torch.zeros([1])
+
+    def remove_weight_norm(self):
+        self.enc.remove_weight_norm()
+
+    def __prepare_scriptable__(self):
+        for hook in self.enc._forward_pre_hooks.values():
+            if (
+                hook.__module__ == "torch.nn.utils.weight_norm"
+                and hook.__class__.__name__ == "WeightNorm"
+            ):
+                torch.nn.utils.remove_weight_norm(self.enc)
+        return self
+
+
+class ConvFlow(nn.Module):
+    def __init__(
+        self,
+        in_channels,
+        filter_channels,
+        kernel_size,
+        n_layers,
+        num_bins=10,
+        tail_bound=5.0,
+    ):
+        super(ConvFlow, self).__init__()
+        self.in_channels = in_channels
+        self.filter_channels = filter_channels
+        self.kernel_size = kernel_size
+        self.n_layers = n_layers
+        self.num_bins = num_bins
+        self.tail_bound = tail_bound
+        self.half_channels = in_channels // 2
+
+        self.pre = nn.Conv1d(self.half_channels, filter_channels, 1)
+        self.convs = DDSConv(filter_channels, kernel_size, n_layers, p_dropout=0.0)
+        self.proj = nn.Conv1d(
+            filter_channels, self.half_channels * (num_bins * 3 - 1), 1
+        )
+        self.proj.weight.data.zero_()
+        self.proj.bias.data.zero_()
+
+    def forward(
+        self,
+        x: torch.Tensor,
+        x_mask: torch.Tensor,
+        g: Optional[torch.Tensor] = None,
+        reverse=False,
+    ):
+        x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
+        h = self.pre(x0)
+        h = self.convs(h, x_mask, g=g)
+        h = self.proj(h) * x_mask
+
+        b, c, t = x0.shape
+        h = h.reshape(b, c, -1, t).permute(0, 1, 3, 2)  # [b, cx?, t] -> [b, c, t, ?]
+
+        unnormalized_widths = h[..., : self.num_bins] / math.sqrt(self.filter_channels)
+        unnormalized_heights = h[..., self.num_bins : 2 * self.num_bins] / math.sqrt(
+            self.filter_channels
+        )
+        unnormalized_derivatives = h[..., 2 * self.num_bins :]
+
+        x1, logabsdet = piecewise_rational_quadratic_transform(
+            x1,
+            unnormalized_widths,
+            unnormalized_heights,
+            unnormalized_derivatives,
+            inverse=reverse,
+            tails="linear",
+            tail_bound=self.tail_bound,
+        )
+
+        x = torch.cat([x0, x1], 1) * x_mask
+        logdet = torch.sum(logabsdet * x_mask, [1, 2])
+        if not reverse:
+            return x, logdet
+        else:
+            return x
diff --git a/rvc/lib/infer_pack/modules/F0Predictor/DioF0Predictor.py b/rvc/lib/infer_pack/modules/F0Predictor/DioF0Predictor.py
new file mode 100644
index 0000000000000000000000000000000000000000..f99f108be8f89daed243a1677a854436d92e814d
--- /dev/null
+++ b/rvc/lib/infer_pack/modules/F0Predictor/DioF0Predictor.py
@@ -0,0 +1,91 @@
+import numpy as np
+import pyworld
+
+from rvc.lib.infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
+
+
+class DioF0Predictor(F0Predictor):
+    def __init__(self, hop_length=512, f0_min=50, f0_max=1100, sampling_rate=44100):
+        self.hop_length = hop_length
+        self.f0_min = f0_min
+        self.f0_max = f0_max
+        self.sampling_rate = sampling_rate
+
+    def interpolate_f0(self, f0):
+        """
+        对F0进行插值处理
+        """
+
+        data = np.reshape(f0, (f0.size, 1))
+
+        vuv_vector = np.zeros((data.size, 1), dtype=np.float32)
+        vuv_vector[data > 0.0] = 1.0
+        vuv_vector[data <= 0.0] = 0.0
+
+        ip_data = data
+
+        frame_number = data.size
+        last_value = 0.0
+        for i in range(frame_number):
+            if data[i] <= 0.0:
+                j = i + 1
+                for j in range(i + 1, frame_number):
+                    if data[j] > 0.0:
+                        break
+                if j < frame_number - 1:
+                    if last_value > 0.0:
+                        step = (data[j] - data[i - 1]) / float(j - i)
+                        for k in range(i, j):
+                            ip_data[k] = data[i - 1] + step * (k - i + 1)
+                    else:
+                        for k in range(i, j):
+                            ip_data[k] = data[j]
+                else:
+                    for k in range(i, frame_number):
+                        ip_data[k] = last_value
+            else:
+                ip_data[i] = data[i]  # 这里可能存在一个没有必要的拷贝
+                last_value = data[i]
+
+        return ip_data[:, 0], vuv_vector[:, 0]
+
+    def resize_f0(self, x, target_len):
+        source = np.array(x)
+        source[source < 0.001] = np.nan
+        target = np.interp(
+            np.arange(0, len(source) * target_len, len(source)) / target_len,
+            np.arange(0, len(source)),
+            source,
+        )
+        res = np.nan_to_num(target)
+        return res
+
+    def compute_f0(self, wav, p_len=None):
+        if p_len is None:
+            p_len = wav.shape[0] // self.hop_length
+        f0, t = pyworld.dio(
+            wav.astype(np.double),
+            fs=self.sampling_rate,
+            f0_floor=self.f0_min,
+            f0_ceil=self.f0_max,
+            frame_period=1000 * self.hop_length / self.sampling_rate,
+        )
+        f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sampling_rate)
+        for index, pitch in enumerate(f0):
+            f0[index] = round(pitch, 1)
+        return self.interpolate_f0(self.resize_f0(f0, p_len))[0]
+
+    def compute_f0_uv(self, wav, p_len=None):
+        if p_len is None:
+            p_len = wav.shape[0] // self.hop_length
+        f0, t = pyworld.dio(
+            wav.astype(np.double),
+            fs=self.sampling_rate,
+            f0_floor=self.f0_min,
+            f0_ceil=self.f0_max,
+            frame_period=1000 * self.hop_length / self.sampling_rate,
+        )
+        f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sampling_rate)
+        for index, pitch in enumerate(f0):
+            f0[index] = round(pitch, 1)
+        return self.interpolate_f0(self.resize_f0(f0, p_len))
diff --git a/rvc/lib/infer_pack/modules/F0Predictor/F0Predictor.py b/rvc/lib/infer_pack/modules/F0Predictor/F0Predictor.py
new file mode 100644
index 0000000000000000000000000000000000000000..0d81b05eef25f0ebeead80bb9baaaef695823b19
--- /dev/null
+++ b/rvc/lib/infer_pack/modules/F0Predictor/F0Predictor.py
@@ -0,0 +1,16 @@
+class F0Predictor(object):
+    def compute_f0(self, wav, p_len):
+        """
+        input: wav:[signal_length]
+               p_len:int
+        output: f0:[signal_length//hop_length]
+        """
+        pass
+
+    def compute_f0_uv(self, wav, p_len):
+        """
+        input: wav:[signal_length]
+               p_len:int
+        output: f0:[signal_length//hop_length],uv:[signal_length//hop_length]
+        """
+        pass
diff --git a/rvc/lib/infer_pack/modules/F0Predictor/HarvestF0Predictor.py b/rvc/lib/infer_pack/modules/F0Predictor/HarvestF0Predictor.py
new file mode 100644
index 0000000000000000000000000000000000000000..6357899627a6427d7f30b94cffe27aa667092fc6
--- /dev/null
+++ b/rvc/lib/infer_pack/modules/F0Predictor/HarvestF0Predictor.py
@@ -0,0 +1,87 @@
+import numpy as np
+import pyworld
+
+from rvc.lib.infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
+
+
+class HarvestF0Predictor(F0Predictor):
+    def __init__(self, hop_length=512, f0_min=50, f0_max=1100, sampling_rate=44100):
+        self.hop_length = hop_length
+        self.f0_min = f0_min
+        self.f0_max = f0_max
+        self.sampling_rate = sampling_rate
+
+    def interpolate_f0(self, f0):
+        """
+        对F0进行插值处理
+        """
+
+        data = np.reshape(f0, (f0.size, 1))
+
+        vuv_vector = np.zeros((data.size, 1), dtype=np.float32)
+        vuv_vector[data > 0.0] = 1.0
+        vuv_vector[data <= 0.0] = 0.0
+
+        ip_data = data
+
+        frame_number = data.size
+        last_value = 0.0
+        for i in range(frame_number):
+            if data[i] <= 0.0:
+                j = i + 1
+                for j in range(i + 1, frame_number):
+                    if data[j] > 0.0:
+                        break
+                if j < frame_number - 1:
+                    if last_value > 0.0:
+                        step = (data[j] - data[i - 1]) / float(j - i)
+                        for k in range(i, j):
+                            ip_data[k] = data[i - 1] + step * (k - i + 1)
+                    else:
+                        for k in range(i, j):
+                            ip_data[k] = data[j]
+                else:
+                    for k in range(i, frame_number):
+                        ip_data[k] = last_value
+            else:
+                ip_data[i] = data[i]  # 这里可能存在一个没有必要的拷贝
+                last_value = data[i]
+
+        return ip_data[:, 0], vuv_vector[:, 0]
+
+    def resize_f0(self, x, target_len):
+        source = np.array(x)
+        source[source < 0.001] = np.nan
+        target = np.interp(
+            np.arange(0, len(source) * target_len, len(source)) / target_len,
+            np.arange(0, len(source)),
+            source,
+        )
+        res = np.nan_to_num(target)
+        return res
+
+    def compute_f0(self, wav, p_len=None):
+        if p_len is None:
+            p_len = wav.shape[0] // self.hop_length
+        f0, t = pyworld.harvest(
+            wav.astype(np.double),
+            fs=self.sampling_rate,
+            f0_ceil=self.f0_max,
+            f0_floor=self.f0_min,
+            frame_period=1000 * self.hop_length / self.sampling_rate,
+        )
+        f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.fs)
+        return self.interpolate_f0(self.resize_f0(f0, p_len))[0]
+
+    def compute_f0_uv(self, wav, p_len=None):
+        if p_len is None:
+            p_len = wav.shape[0] // self.hop_length
+        f0, t = pyworld.harvest(
+            wav.astype(np.double),
+            fs=self.sampling_rate,
+            f0_floor=self.f0_min,
+            f0_ceil=self.f0_max,
+            frame_period=1000 * self.hop_length / self.sampling_rate,
+        )
+        f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sampling_rate)
+        return self.interpolate_f0(self.resize_f0(f0, p_len))
diff --git a/rvc/lib/infer_pack/modules/F0Predictor/PMF0Predictor.py b/rvc/lib/infer_pack/modules/F0Predictor/PMF0Predictor.py
new file mode 100644
index 0000000000000000000000000000000000000000..75987ffe561474382dd14c3c545cad9661f5e211
--- /dev/null
+++ b/rvc/lib/infer_pack/modules/F0Predictor/PMF0Predictor.py
@@ -0,0 +1,98 @@
+import numpy as np
+import parselmouth
+
+from rvc.lib.infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
+
+
+class PMF0Predictor(F0Predictor):
+    def __init__(self, hop_length=512, f0_min=50, f0_max=1100, sampling_rate=44100):
+        self.hop_length = hop_length
+        self.f0_min = f0_min
+        self.f0_max = f0_max
+        self.sampling_rate = sampling_rate
+
+    def interpolate_f0(self, f0):
+        """
+        对F0进行插值处理
+        """
+
+        data = np.reshape(f0, (f0.size, 1))
+
+        vuv_vector = np.zeros((data.size, 1), dtype=np.float32)
+        vuv_vector[data > 0.0] = 1.0
+        vuv_vector[data <= 0.0] = 0.0
+
+        ip_data = data
+
+        frame_number = data.size
+        last_value = 0.0
+        for i in range(frame_number):
+            if data[i] <= 0.0:
+                j = i + 1
+                for j in range(i + 1, frame_number):
+                    if data[j] > 0.0:
+                        break
+                if j < frame_number - 1:
+                    if last_value > 0.0:
+                        step = (data[j] - data[i - 1]) / float(j - i)
+                        for k in range(i, j):
+                            ip_data[k] = data[i - 1] + step * (k - i + 1)
+                    else:
+                        for k in range(i, j):
+                            ip_data[k] = data[j]
+                else:
+                    for k in range(i, frame_number):
+                        ip_data[k] = last_value
+            else:
+                ip_data[i] = data[i]  # 这里可能存在一个没有必要的拷贝
+                last_value = data[i]
+
+        return ip_data[:, 0], vuv_vector[:, 0]
+
+    def compute_f0(self, wav, p_len=None):
+        x = wav
+        if p_len is None:
+            p_len = x.shape[0] // self.hop_length
+        else:
+            assert abs(p_len - x.shape[0] // self.hop_length) < 4, "pad length error"
+        time_step = self.hop_length / self.sampling_rate * 1000
+        f0 = (
+            parselmouth.Sound(x, self.sampling_rate)
+            .to_pitch_ac(
+                time_step=time_step / 1000,
+                voicing_threshold=0.6,
+                pitch_floor=self.f0_min,
+                pitch_ceiling=self.f0_max,
+            )
+            .selected_array["frequency"]
+        )
+
+        pad_size = (p_len - len(f0) + 1) // 2
+        if pad_size > 0 or p_len - len(f0) - pad_size > 0:
+            f0 = np.pad(f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant")
+        f0, uv = self.interpolate_f0(f0)
+        return f0
+
+    def compute_f0_uv(self, wav, p_len=None):
+        x = wav
+        if p_len is None:
+            p_len = x.shape[0] // self.hop_length
+        else:
+            assert abs(p_len - x.shape[0] // self.hop_length) < 4, "pad length error"
+        time_step = self.hop_length / self.sampling_rate * 1000
+        f0 = (
+            parselmouth.Sound(x, self.sampling_rate)
+            .to_pitch_ac(
+                time_step=time_step / 1000,
+                voicing_threshold=0.6,
+                pitch_floor=self.f0_min,
+                pitch_ceiling=self.f0_max,
+            )
+            .selected_array["frequency"]
+        )
+
+        pad_size = (p_len - len(f0) + 1) // 2
+        if pad_size > 0 or p_len - len(f0) - pad_size > 0:
+            f0 = np.pad(f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant")
+        f0, uv = self.interpolate_f0(f0)
+        return f0, uv
diff --git a/rvc/lib/infer_pack/modules/F0Predictor/__init__.py b/rvc/lib/infer_pack/modules/F0Predictor/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/rvc/lib/infer_pack/onnx_inference.py b/rvc/lib/infer_pack/onnx_inference.py
new file mode 100644
index 0000000000000000000000000000000000000000..86e258384966e606300e32efe5dc0205128a28ea
--- /dev/null
+++ b/rvc/lib/infer_pack/onnx_inference.py
@@ -0,0 +1,149 @@
+import logging
+
+import librosa
+import numpy as np
+import onnxruntime
+import soundfile
+
+logger = logging.getLogger(__name__)
+
+
+class ContentVec:
+    def __init__(self, vec_path="pretrained/vec-768-layer-12.onnx", device=None):
+        logger.info("Load model(s) from {}".format(vec_path))
+        if device == "cpu" or device is None:
+            providers = ["CPUExecutionProvider"]
+        elif device == "cuda":
+            providers = ["CUDAExecutionProvider", "CPUExecutionProvider"]
+        elif device == "dml":
+            providers = ["DmlExecutionProvider"]
+        else:
+            raise RuntimeError("Unsportted Device")
+        self.model = onnxruntime.InferenceSession(vec_path, providers=providers)
+
+    def __call__(self, wav):
+        return self.forward(wav)
+
+    def forward(self, wav):
+        feats = wav
+        if feats.ndim == 2:  # double channels
+            feats = feats.mean(-1)
+        assert feats.ndim == 1, feats.ndim
+        feats = np.expand_dims(np.expand_dims(feats, 0), 0)
+        onnx_input = {self.model.get_inputs()[0].name: feats}
+        logits = self.model.run(None, onnx_input)[0]
+        return logits.transpose(0, 2, 1)
+
+
+def get_f0_predictor(f0_predictor, hop_length, sampling_rate, **kargs):
+    if f0_predictor == "pm":
+        from lib.infer_pack.modules.F0Predictor.PMF0Predictor import PMF0Predictor
+
+        f0_predictor_object = PMF0Predictor(
+            hop_length=hop_length, sampling_rate=sampling_rate
+        )
+    elif f0_predictor == "harvest":
+        from lib.infer_pack.modules.F0Predictor.HarvestF0Predictor import (
+            HarvestF0Predictor,
+        )
+
+        f0_predictor_object = HarvestF0Predictor(
+            hop_length=hop_length, sampling_rate=sampling_rate
+        )
+    elif f0_predictor == "dio":
+        from lib.infer_pack.modules.F0Predictor.DioF0Predictor import DioF0Predictor
+
+        f0_predictor_object = DioF0Predictor(
+            hop_length=hop_length, sampling_rate=sampling_rate
+        )
+    else:
+        raise Exception("Unknown f0 predictor")
+    return f0_predictor_object
+
+
+class OnnxRVC:
+    def __init__(
+        self,
+        model_path,
+        sr=40000,
+        hop_size=512,
+        vec_path="vec-768-layer-12",
+        device="cpu",
+    ):
+        vec_path = f"pretrained/{vec_path}.onnx"
+        self.vec_model = ContentVec(vec_path, device)
+        if device == "cpu" or device is None:
+            providers = ["CPUExecutionProvider"]
+        elif device == "cuda":
+            providers = ["CUDAExecutionProvider", "CPUExecutionProvider"]
+        elif device == "dml":
+            providers = ["DmlExecutionProvider"]
+        else:
+            raise RuntimeError("Unsportted Device")
+        self.model = onnxruntime.InferenceSession(model_path, providers=providers)
+        self.sampling_rate = sr
+        self.hop_size = hop_size
+
+    def forward(self, hubert, hubert_length, pitch, pitchf, ds, rnd):
+        onnx_input = {
+            self.model.get_inputs()[0].name: hubert,
+            self.model.get_inputs()[1].name: hubert_length,
+            self.model.get_inputs()[2].name: pitch,
+            self.model.get_inputs()[3].name: pitchf,
+            self.model.get_inputs()[4].name: ds,
+            self.model.get_inputs()[5].name: rnd,
+        }
+        return (self.model.run(None, onnx_input)[0] * 32767).astype(np.int16)
+
+    def inference(
+        self,
+        raw_path,
+        sid,
+        f0_method="dio",
+        f0_up_key=0,
+        pad_time=0.5,
+        cr_threshold=0.02,
+    ):
+        f0_min = 50
+        f0_max = 1100
+        f0_mel_min = 1127 * np.log(1 + f0_min / 700)
+        f0_mel_max = 1127 * np.log(1 + f0_max / 700)
+        f0_predictor = get_f0_predictor(
+            f0_method,
+            hop_length=self.hop_size,
+            sampling_rate=self.sampling_rate,
+            threshold=cr_threshold,
+        )
+        wav, sr = librosa.load(raw_path, sr=self.sampling_rate)
+        org_length = len(wav)
+        if org_length / sr > 50.0:
+            raise RuntimeError("Reached Max Length")
+
+        wav16k = librosa.resample(wav, orig_sr=self.sampling_rate, target_sr=16000)
+        wav16k = wav16k
+
+        hubert = self.vec_model(wav16k)
+        hubert = np.repeat(hubert, 2, axis=2).transpose(0, 2, 1).astype(np.float32)
+        hubert_length = hubert.shape[1]
+
+        pitchf = f0_predictor.compute_f0(wav, hubert_length)
+        pitchf = pitchf * 2 ** (f0_up_key / 12)
+        pitch = pitchf.copy()
+        f0_mel = 1127 * np.log(1 + pitch / 700)
+        f0_mel[f0_mel > 0] = (f0_mel[f0_mel > 0] - f0_mel_min) * 254 / (
+            f0_mel_max - f0_mel_min
+        ) + 1
+        f0_mel[f0_mel <= 1] = 1
+        f0_mel[f0_mel > 255] = 255
+        pitch = np.rint(f0_mel).astype(np.int64)
+
+        pitchf = pitchf.reshape(1, len(pitchf)).astype(np.float32)
+        pitch = pitch.reshape(1, len(pitch))
+        ds = np.array([sid]).astype(np.int64)
+
+        rnd = np.random.randn(1, 192, hubert_length).astype(np.float32)
+        hubert_length = np.array([hubert_length]).astype(np.int64)
+
+        out_wav = self.forward(hubert, hubert_length, pitch, pitchf, ds, rnd).squeeze()
+        out_wav = np.pad(out_wav, (0, 2 * self.hop_size), "constant")
+        return out_wav[0:org_length]
diff --git a/rvc/lib/infer_pack/transforms.py b/rvc/lib/infer_pack/transforms.py
new file mode 100644
index 0000000000000000000000000000000000000000..6d07b3b12cee87869440feb1496dd634d334e96f
--- /dev/null
+++ b/rvc/lib/infer_pack/transforms.py
@@ -0,0 +1,207 @@
+import numpy as np
+import torch
+from torch.nn import functional as F
+
+DEFAULT_MIN_BIN_WIDTH = 1e-3
+DEFAULT_MIN_BIN_HEIGHT = 1e-3
+DEFAULT_MIN_DERIVATIVE = 1e-3
+
+
+def piecewise_rational_quadratic_transform(
+    inputs,
+    unnormalized_widths,
+    unnormalized_heights,
+    unnormalized_derivatives,
+    inverse=False,
+    tails=None,
+    tail_bound=1.0,
+    min_bin_width=DEFAULT_MIN_BIN_WIDTH,
+    min_bin_height=DEFAULT_MIN_BIN_HEIGHT,
+    min_derivative=DEFAULT_MIN_DERIVATIVE,
+):
+    if tails is None:
+        spline_fn = rational_quadratic_spline
+        spline_kwargs = {}
+    else:
+        spline_fn = unconstrained_rational_quadratic_spline
+        spline_kwargs = {"tails": tails, "tail_bound": tail_bound}
+
+    outputs, logabsdet = spline_fn(
+        inputs=inputs,
+        unnormalized_widths=unnormalized_widths,
+        unnormalized_heights=unnormalized_heights,
+        unnormalized_derivatives=unnormalized_derivatives,
+        inverse=inverse,
+        min_bin_width=min_bin_width,
+        min_bin_height=min_bin_height,
+        min_derivative=min_derivative,
+        **spline_kwargs
+    )
+    return outputs, logabsdet
+
+
+def searchsorted(bin_locations, inputs, eps=1e-6):
+    bin_locations[..., -1] += eps
+    return torch.sum(inputs[..., None] >= bin_locations, dim=-1) - 1
+
+
+def unconstrained_rational_quadratic_spline(
+    inputs,
+    unnormalized_widths,
+    unnormalized_heights,
+    unnormalized_derivatives,
+    inverse=False,
+    tails="linear",
+    tail_bound=1.0,
+    min_bin_width=DEFAULT_MIN_BIN_WIDTH,
+    min_bin_height=DEFAULT_MIN_BIN_HEIGHT,
+    min_derivative=DEFAULT_MIN_DERIVATIVE,
+):
+    inside_interval_mask = (inputs >= -tail_bound) & (inputs <= tail_bound)
+    outside_interval_mask = ~inside_interval_mask
+
+    outputs = torch.zeros_like(inputs)
+    logabsdet = torch.zeros_like(inputs)
+
+    if tails == "linear":
+        unnormalized_derivatives = F.pad(unnormalized_derivatives, pad=(1, 1))
+        constant = np.log(np.exp(1 - min_derivative) - 1)
+        unnormalized_derivatives[..., 0] = constant
+        unnormalized_derivatives[..., -1] = constant
+
+        outputs[outside_interval_mask] = inputs[outside_interval_mask]
+        logabsdet[outside_interval_mask] = 0
+    else:
+        raise RuntimeError("{} tails are not implemented.".format(tails))
+
+    (
+        outputs[inside_interval_mask],
+        logabsdet[inside_interval_mask],
+    ) = rational_quadratic_spline(
+        inputs=inputs[inside_interval_mask],
+        unnormalized_widths=unnormalized_widths[inside_interval_mask, :],
+        unnormalized_heights=unnormalized_heights[inside_interval_mask, :],
+        unnormalized_derivatives=unnormalized_derivatives[inside_interval_mask, :],
+        inverse=inverse,
+        left=-tail_bound,
+        right=tail_bound,
+        bottom=-tail_bound,
+        top=tail_bound,
+        min_bin_width=min_bin_width,
+        min_bin_height=min_bin_height,
+        min_derivative=min_derivative,
+    )
+
+    return outputs, logabsdet
+
+
+def rational_quadratic_spline(
+    inputs,
+    unnormalized_widths,
+    unnormalized_heights,
+    unnormalized_derivatives,
+    inverse=False,
+    left=0.0,
+    right=1.0,
+    bottom=0.0,
+    top=1.0,
+    min_bin_width=DEFAULT_MIN_BIN_WIDTH,
+    min_bin_height=DEFAULT_MIN_BIN_HEIGHT,
+    min_derivative=DEFAULT_MIN_DERIVATIVE,
+):
+    if torch.min(inputs) < left or torch.max(inputs) > right:
+        raise ValueError("Input to a transform is not within its domain")
+
+    num_bins = unnormalized_widths.shape[-1]
+
+    if min_bin_width * num_bins > 1.0:
+        raise ValueError("Minimal bin width too large for the number of bins")
+    if min_bin_height * num_bins > 1.0:
+        raise ValueError("Minimal bin height too large for the number of bins")
+
+    widths = F.softmax(unnormalized_widths, dim=-1)
+    widths = min_bin_width + (1 - min_bin_width * num_bins) * widths
+    cumwidths = torch.cumsum(widths, dim=-1)
+    cumwidths = F.pad(cumwidths, pad=(1, 0), mode="constant", value=0.0)
+    cumwidths = (right - left) * cumwidths + left
+    cumwidths[..., 0] = left
+    cumwidths[..., -1] = right
+    widths = cumwidths[..., 1:] - cumwidths[..., :-1]
+
+    derivatives = min_derivative + F.softplus(unnormalized_derivatives)
+
+    heights = F.softmax(unnormalized_heights, dim=-1)
+    heights = min_bin_height + (1 - min_bin_height * num_bins) * heights
+    cumheights = torch.cumsum(heights, dim=-1)
+    cumheights = F.pad(cumheights, pad=(1, 0), mode="constant", value=0.0)
+    cumheights = (top - bottom) * cumheights + bottom
+    cumheights[..., 0] = bottom
+    cumheights[..., -1] = top
+    heights = cumheights[..., 1:] - cumheights[..., :-1]
+
+    if inverse:
+        bin_idx = searchsorted(cumheights, inputs)[..., None]
+    else:
+        bin_idx = searchsorted(cumwidths, inputs)[..., None]
+
+    input_cumwidths = cumwidths.gather(-1, bin_idx)[..., 0]
+    input_bin_widths = widths.gather(-1, bin_idx)[..., 0]
+
+    input_cumheights = cumheights.gather(-1, bin_idx)[..., 0]
+    delta = heights / widths
+    input_delta = delta.gather(-1, bin_idx)[..., 0]
+
+    input_derivatives = derivatives.gather(-1, bin_idx)[..., 0]
+    input_derivatives_plus_one = derivatives[..., 1:].gather(-1, bin_idx)[..., 0]
+
+    input_heights = heights.gather(-1, bin_idx)[..., 0]
+
+    if inverse:
+        a = (inputs - input_cumheights) * (
+            input_derivatives + input_derivatives_plus_one - 2 * input_delta
+        ) + input_heights * (input_delta - input_derivatives)
+        b = input_heights * input_derivatives - (inputs - input_cumheights) * (
+            input_derivatives + input_derivatives_plus_one - 2 * input_delta
+        )
+        c = -input_delta * (inputs - input_cumheights)
+
+        discriminant = b.pow(2) - 4 * a * c
+        assert (discriminant >= 0).all()
+
+        root = (2 * c) / (-b - torch.sqrt(discriminant))
+        outputs = root * input_bin_widths + input_cumwidths
+
+        theta_one_minus_theta = root * (1 - root)
+        denominator = input_delta + (
+            (input_derivatives + input_derivatives_plus_one - 2 * input_delta)
+            * theta_one_minus_theta
+        )
+        derivative_numerator = input_delta.pow(2) * (
+            input_derivatives_plus_one * root.pow(2)
+            + 2 * input_delta * theta_one_minus_theta
+            + input_derivatives * (1 - root).pow(2)
+        )
+        logabsdet = torch.log(derivative_numerator) - 2 * torch.log(denominator)
+
+        return outputs, -logabsdet
+    else:
+        theta = (inputs - input_cumwidths) / input_bin_widths
+        theta_one_minus_theta = theta * (1 - theta)
+
+        numerator = input_heights * (
+            input_delta * theta.pow(2) + input_derivatives * theta_one_minus_theta
+        )
+        denominator = input_delta + (
+            (input_derivatives + input_derivatives_plus_one - 2 * input_delta)
+            * theta_one_minus_theta
+        )
+        outputs = input_cumheights + numerator / denominator
+
+        derivative_numerator = input_delta.pow(2) * (
+            input_derivatives_plus_one * theta.pow(2)
+            + 2 * input_delta * theta_one_minus_theta
+            + input_derivatives * (1 - theta).pow(2)
+        )
+        logabsdet = torch.log(derivative_numerator) - 2 * torch.log(denominator)
+
+        return outputs, logabsdet
diff --git a/rvc/lib/ipex/__init__.py b/rvc/lib/ipex/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e472362d58973c21b719cc7c2d2fe6d7bc981338
--- /dev/null
+++ b/rvc/lib/ipex/__init__.py
@@ -0,0 +1,182 @@
+import contextlib
+import os
+import sys
+
+import intel_extension_for_pytorch as ipex  # pylint: disable=import-error, unused-import
+import torch
+
+from .attention import attention_init
+from .hijacks import ipex_hijacks
+
+
+def ipex_init():
+    try:
+        # Replace cuda with xpu:
+        torch.cuda.current_device = torch.xpu.current_device
+        torch.cuda.current_stream = torch.xpu.current_stream
+        torch.cuda.device = torch.xpu.device
+        torch.cuda.device_count = torch.xpu.device_count
+        torch.cuda.device_of = torch.xpu.device_of
+        torch.cuda.get_device_name = torch.xpu.get_device_name
+        torch.cuda.get_device_properties = torch.xpu.get_device_properties
+        torch.cuda.init = torch.xpu.init
+        torch.cuda.is_available = torch.xpu.is_available
+        torch.cuda.is_initialized = torch.xpu.is_initialized
+        torch.cuda.is_current_stream_capturing = lambda: False
+        torch.cuda.set_device = torch.xpu.set_device
+        torch.cuda.stream = torch.xpu.stream
+        torch.cuda.synchronize = torch.xpu.synchronize
+        torch.cuda.Event = torch.xpu.Event
+        torch.cuda.Stream = torch.xpu.Stream
+        torch.cuda.FloatTensor = torch.xpu.FloatTensor
+        torch.Tensor.cuda = torch.Tensor.xpu
+        torch.Tensor.is_cuda = torch.Tensor.is_xpu
+        torch.cuda._initialization_lock = torch.xpu.lazy_init._initialization_lock
+        torch.cuda._initialized = torch.xpu.lazy_init._initialized
+        torch.cuda._lazy_seed_tracker = torch.xpu.lazy_init._lazy_seed_tracker
+        torch.cuda._queued_calls = torch.xpu.lazy_init._queued_calls
+        torch.cuda._tls = torch.xpu.lazy_init._tls
+        torch.cuda.threading = torch.xpu.lazy_init.threading
+        torch.cuda.traceback = torch.xpu.lazy_init.traceback
+        torch.cuda.Optional = torch.xpu.Optional
+        torch.cuda.__cached__ = torch.xpu.__cached__
+        torch.cuda.__loader__ = torch.xpu.__loader__
+        torch.cuda.ComplexFloatStorage = torch.xpu.ComplexFloatStorage
+        torch.cuda.Tuple = torch.xpu.Tuple
+        torch.cuda.streams = torch.xpu.streams
+        torch.cuda._lazy_new = torch.xpu._lazy_new
+        torch.cuda.FloatStorage = torch.xpu.FloatStorage
+        torch.cuda.Any = torch.xpu.Any
+        torch.cuda.__doc__ = torch.xpu.__doc__
+        torch.cuda.default_generators = torch.xpu.default_generators
+        torch.cuda.HalfTensor = torch.xpu.HalfTensor
+        torch.cuda._get_device_index = torch.xpu._get_device_index
+        torch.cuda.__path__ = torch.xpu.__path__
+        torch.cuda.Device = torch.xpu.Device
+        torch.cuda.IntTensor = torch.xpu.IntTensor
+        torch.cuda.ByteStorage = torch.xpu.ByteStorage
+        torch.cuda.set_stream = torch.xpu.set_stream
+        torch.cuda.BoolStorage = torch.xpu.BoolStorage
+        torch.cuda.os = torch.xpu.os
+        torch.cuda.torch = torch.xpu.torch
+        torch.cuda.BFloat16Storage = torch.xpu.BFloat16Storage
+        torch.cuda.Union = torch.xpu.Union
+        torch.cuda.DoubleTensor = torch.xpu.DoubleTensor
+        torch.cuda.ShortTensor = torch.xpu.ShortTensor
+        torch.cuda.LongTensor = torch.xpu.LongTensor
+        torch.cuda.IntStorage = torch.xpu.IntStorage
+        torch.cuda.LongStorage = torch.xpu.LongStorage
+        torch.cuda.__annotations__ = torch.xpu.__annotations__
+        torch.cuda.__package__ = torch.xpu.__package__
+        torch.cuda.__builtins__ = torch.xpu.__builtins__
+        torch.cuda.CharTensor = torch.xpu.CharTensor
+        torch.cuda.List = torch.xpu.List
+        torch.cuda._lazy_init = torch.xpu._lazy_init
+        torch.cuda.BFloat16Tensor = torch.xpu.BFloat16Tensor
+        torch.cuda.DoubleStorage = torch.xpu.DoubleStorage
+        torch.cuda.ByteTensor = torch.xpu.ByteTensor
+        torch.cuda.StreamContext = torch.xpu.StreamContext
+        torch.cuda.ComplexDoubleStorage = torch.xpu.ComplexDoubleStorage
+        torch.cuda.ShortStorage = torch.xpu.ShortStorage
+        torch.cuda._lazy_call = torch.xpu._lazy_call
+        torch.cuda.HalfStorage = torch.xpu.HalfStorage
+        torch.cuda.random = torch.xpu.random
+        torch.cuda._device = torch.xpu._device
+        torch.cuda.classproperty = torch.xpu.classproperty
+        torch.cuda.__name__ = torch.xpu.__name__
+        torch.cuda._device_t = torch.xpu._device_t
+        torch.cuda.warnings = torch.xpu.warnings
+        torch.cuda.__spec__ = torch.xpu.__spec__
+        torch.cuda.BoolTensor = torch.xpu.BoolTensor
+        torch.cuda.CharStorage = torch.xpu.CharStorage
+        torch.cuda.__file__ = torch.xpu.__file__
+        torch.cuda._is_in_bad_fork = torch.xpu.lazy_init._is_in_bad_fork
+        # torch.cuda.is_current_stream_capturing = torch.xpu.is_current_stream_capturing
+
+        # Memory:
+        torch.cuda.memory = torch.xpu.memory
+        if "linux" in sys.platform and "WSL2" in os.popen("uname -a").read():
+            torch.xpu.empty_cache = lambda: None
+        torch.cuda.empty_cache = torch.xpu.empty_cache
+        torch.cuda.memory_stats = torch.xpu.memory_stats
+        torch.cuda.memory_summary = torch.xpu.memory_summary
+        torch.cuda.memory_snapshot = torch.xpu.memory_snapshot
+        torch.cuda.memory_allocated = torch.xpu.memory_allocated
+        torch.cuda.max_memory_allocated = torch.xpu.max_memory_allocated
+        torch.cuda.memory_reserved = torch.xpu.memory_reserved
+        torch.cuda.memory_cached = torch.xpu.memory_reserved
+        torch.cuda.max_memory_reserved = torch.xpu.max_memory_reserved
+        torch.cuda.max_memory_cached = torch.xpu.max_memory_reserved
+        torch.cuda.reset_peak_memory_stats = torch.xpu.reset_peak_memory_stats
+        torch.cuda.reset_max_memory_cached = torch.xpu.reset_peak_memory_stats
+        torch.cuda.reset_max_memory_allocated = torch.xpu.reset_peak_memory_stats
+        torch.cuda.memory_stats_as_nested_dict = torch.xpu.memory_stats_as_nested_dict
+        torch.cuda.reset_accumulated_memory_stats = (
+            torch.xpu.reset_accumulated_memory_stats
+        )
+
+        # RNG:
+        torch.cuda.get_rng_state = torch.xpu.get_rng_state
+        torch.cuda.get_rng_state_all = torch.xpu.get_rng_state_all
+        torch.cuda.set_rng_state = torch.xpu.set_rng_state
+        torch.cuda.set_rng_state_all = torch.xpu.set_rng_state_all
+        torch.cuda.manual_seed = torch.xpu.manual_seed
+        torch.cuda.manual_seed_all = torch.xpu.manual_seed_all
+        torch.cuda.seed = torch.xpu.seed
+        torch.cuda.seed_all = torch.xpu.seed_all
+        torch.cuda.initial_seed = torch.xpu.initial_seed
+
+        # AMP:
+        torch.cuda.amp = torch.xpu.amp
+        if not hasattr(torch.cuda.amp, "common"):
+            torch.cuda.amp.common = contextlib.nullcontext()
+        torch.cuda.amp.common.amp_definitely_not_available = lambda: False
+        try:
+            torch.cuda.amp.GradScaler = torch.xpu.amp.GradScaler
+        except Exception:
+            try:
+                from .gradscaler import gradscaler_init
+
+                gradscaler_init()
+                torch.cuda.amp.GradScaler = torch.xpu.amp.GradScaler
+            except Exception:
+                torch.cuda.amp.GradScaler = ipex.cpu.autocast._grad_scaler.GradScaler
+
+        # C
+        torch._C._cuda_getCurrentRawStream = ipex._C._getCurrentStream
+        ipex._C._DeviceProperties.major = 2023
+        ipex._C._DeviceProperties.minor = 2
+
+        # Fix functions with ipex:
+        torch.cuda.mem_get_info = lambda device=None: [
+            (
+                torch.xpu.get_device_properties(device).total_memory
+                - torch.xpu.memory_allocated(device)
+            ),
+            torch.xpu.get_device_properties(device).total_memory,
+        ]
+        torch._utils._get_available_device_type = lambda: "xpu"
+        torch.has_cuda = True
+        torch.cuda.has_half = True
+        torch.cuda.is_bf16_supported = lambda *args, **kwargs: True
+        torch.cuda.is_fp16_supported = lambda *args, **kwargs: True
+        torch.version.cuda = "11.7"
+        torch.cuda.get_device_capability = lambda *args, **kwargs: [11, 7]
+        torch.cuda.get_device_properties.major = 11
+        torch.cuda.get_device_properties.minor = 7
+        torch.cuda.ipc_collect = lambda *args, **kwargs: None
+        torch.cuda.utilization = lambda *args, **kwargs: 0
+        if hasattr(torch.xpu, "getDeviceIdListForCard"):
+            torch.cuda.getDeviceIdListForCard = torch.xpu.getDeviceIdListForCard
+            torch.cuda.get_device_id_list_per_card = torch.xpu.getDeviceIdListForCard
+        else:
+            torch.cuda.getDeviceIdListForCard = torch.xpu.get_device_id_list_per_card
+            torch.cuda.get_device_id_list_per_card = (
+                torch.xpu.get_device_id_list_per_card
+            )
+
+        ipex_hijacks()
+        attention_init()
+    except Exception as e:
+        return False, e
+    return True, None
diff --git a/rvc/lib/ipex/attention.py b/rvc/lib/ipex/attention.py
new file mode 100644
index 0000000000000000000000000000000000000000..af36193ef719482ff97b7bc0d6752c55ecbf61af
--- /dev/null
+++ b/rvc/lib/ipex/attention.py
@@ -0,0 +1,206 @@
+import intel_extension_for_pytorch as ipex
+import torch
+
+original_torch_bmm = torch.bmm
+
+
+def torch_bmm(input, mat2, *, out=None):
+    if input.dtype != mat2.dtype:
+        mat2 = mat2.to(input.dtype)
+
+    # ARC GPUs can't allocate more than 4GB to a single block, Slice it:
+    batch_size_attention, input_tokens, mat2_shape = (
+        input.shape[0],
+        input.shape[1],
+        mat2.shape[2],
+    )
+    block_multiply = input.element_size()
+    slice_block_size = input_tokens * mat2_shape / 1024 / 1024 * block_multiply
+    block_size = batch_size_attention * slice_block_size
+
+    split_slice_size = batch_size_attention
+    if block_size > 4:
+        do_split = True
+        # Find something divisible with the input_tokens
+        while (split_slice_size * slice_block_size) > 4:
+            split_slice_size = split_slice_size // 2
+            if split_slice_size <= 1:
+                split_slice_size = 1
+                break
+    else:
+        do_split = False
+
+    split_2_slice_size = input_tokens
+    if split_slice_size * slice_block_size > 4:
+        slice_block_size2 = split_slice_size * mat2_shape / 1024 / 1024 * block_multiply
+        do_split_2 = True
+        # Find something divisible with the input_tokens
+        while (split_2_slice_size * slice_block_size2) > 4:
+            split_2_slice_size = split_2_slice_size // 2
+            if split_2_slice_size <= 1:
+                split_2_slice_size = 1
+                break
+    else:
+        do_split_2 = False
+
+    if do_split:
+        hidden_states = torch.zeros(
+            input.shape[0],
+            input.shape[1],
+            mat2.shape[2],
+            device=input.device,
+            dtype=input.dtype,
+        )
+        for i in range(batch_size_attention // split_slice_size):
+            start_idx = i * split_slice_size
+            end_idx = (i + 1) * split_slice_size
+            if do_split_2:
+                for i2 in range(input_tokens // split_2_slice_size):
+                    start_idx_2 = i2 * split_2_slice_size
+                    end_idx_2 = (i2 + 1) * split_2_slice_size
+                    hidden_states[
+                        start_idx:end_idx, start_idx_2:end_idx_2
+                    ] = original_torch_bmm(
+                        input[start_idx:end_idx, start_idx_2:end_idx_2],
+                        mat2[start_idx:end_idx, start_idx_2:end_idx_2],
+                        out=out,
+                    )
+            else:
+                hidden_states[start_idx:end_idx] = original_torch_bmm(
+                    input[start_idx:end_idx], mat2[start_idx:end_idx], out=out
+                )
+    else:
+        return original_torch_bmm(input, mat2, out=out)
+    return hidden_states
+
+
+original_scaled_dot_product_attention = torch.nn.functional.scaled_dot_product_attention
+
+
+def scaled_dot_product_attention(
+    query, key, value, attn_mask=None, dropout_p=0.0, is_causal=False
+):
+    # ARC GPUs can't allocate more than 4GB to a single block, Slice it:
+    if len(query.shape) == 3:
+        batch_size_attention, query_tokens, shape_four = query.shape
+        shape_one = 1
+        no_shape_one = True
+    else:
+        shape_one, batch_size_attention, query_tokens, shape_four = query.shape
+        no_shape_one = False
+
+    block_multiply = query.element_size()
+    slice_block_size = (
+        shape_one * query_tokens * shape_four / 1024 / 1024 * block_multiply
+    )
+    block_size = batch_size_attention * slice_block_size
+
+    split_slice_size = batch_size_attention
+    if block_size > 4:
+        do_split = True
+        # Find something divisible with the shape_one
+        while (split_slice_size * slice_block_size) > 4:
+            split_slice_size = split_slice_size // 2
+            if split_slice_size <= 1:
+                split_slice_size = 1
+                break
+    else:
+        do_split = False
+
+    split_2_slice_size = query_tokens
+    if split_slice_size * slice_block_size > 4:
+        slice_block_size2 = (
+            shape_one * split_slice_size * shape_four / 1024 / 1024 * block_multiply
+        )
+        do_split_2 = True
+        # Find something divisible with the batch_size_attention
+        while (split_2_slice_size * slice_block_size2) > 4:
+            split_2_slice_size = split_2_slice_size // 2
+            if split_2_slice_size <= 1:
+                split_2_slice_size = 1
+                break
+    else:
+        do_split_2 = False
+
+    if do_split:
+        hidden_states = torch.zeros(query.shape, device=query.device, dtype=query.dtype)
+        for i in range(batch_size_attention // split_slice_size):
+            start_idx = i * split_slice_size
+            end_idx = (i + 1) * split_slice_size
+            if do_split_2:
+                for i2 in range(query_tokens // split_2_slice_size):
+                    start_idx_2 = i2 * split_2_slice_size
+                    end_idx_2 = (i2 + 1) * split_2_slice_size
+                    if no_shape_one:
+                        hidden_states[
+                            start_idx:end_idx, start_idx_2:end_idx_2
+                        ] = original_scaled_dot_product_attention(
+                            query[start_idx:end_idx, start_idx_2:end_idx_2],
+                            key[start_idx:end_idx, start_idx_2:end_idx_2],
+                            value[start_idx:end_idx, start_idx_2:end_idx_2],
+                            attn_mask=attn_mask[
+                                start_idx:end_idx, start_idx_2:end_idx_2
+                            ]
+                            if attn_mask is not None
+                            else attn_mask,
+                            dropout_p=dropout_p,
+                            is_causal=is_causal,
+                        )
+                    else:
+                        hidden_states[
+                            :, start_idx:end_idx, start_idx_2:end_idx_2
+                        ] = original_scaled_dot_product_attention(
+                            query[:, start_idx:end_idx, start_idx_2:end_idx_2],
+                            key[:, start_idx:end_idx, start_idx_2:end_idx_2],
+                            value[:, start_idx:end_idx, start_idx_2:end_idx_2],
+                            attn_mask=attn_mask[
+                                :, start_idx:end_idx, start_idx_2:end_idx_2
+                            ]
+                            if attn_mask is not None
+                            else attn_mask,
+                            dropout_p=dropout_p,
+                            is_causal=is_causal,
+                        )
+            else:
+                if no_shape_one:
+                    hidden_states[
+                        start_idx:end_idx
+                    ] = original_scaled_dot_product_attention(
+                        query[start_idx:end_idx],
+                        key[start_idx:end_idx],
+                        value[start_idx:end_idx],
+                        attn_mask=attn_mask[start_idx:end_idx]
+                        if attn_mask is not None
+                        else attn_mask,
+                        dropout_p=dropout_p,
+                        is_causal=is_causal,
+                    )
+                else:
+                    hidden_states[
+                        :, start_idx:end_idx
+                    ] = original_scaled_dot_product_attention(
+                        query[:, start_idx:end_idx],
+                        key[:, start_idx:end_idx],
+                        value[:, start_idx:end_idx],
+                        attn_mask=attn_mask[:, start_idx:end_idx]
+                        if attn_mask is not None
+                        else attn_mask,
+                        dropout_p=dropout_p,
+                        is_causal=is_causal,
+                    )
+    else:
+        return original_scaled_dot_product_attention(
+            query,
+            key,
+            value,
+            attn_mask=attn_mask,
+            dropout_p=dropout_p,
+            is_causal=is_causal,
+        )
+    return hidden_states
+
+
+def attention_init():
+    # ARC GPUs can't allocate more than 4GB to a single block:
+    torch.bmm = torch_bmm
+    torch.nn.functional.scaled_dot_product_attention = scaled_dot_product_attention
diff --git a/rvc/lib/ipex/gradscaler.py b/rvc/lib/ipex/gradscaler.py
new file mode 100644
index 0000000000000000000000000000000000000000..412226453f701fe8547fbc184c3ee9bbcc3f4d34
--- /dev/null
+++ b/rvc/lib/ipex/gradscaler.py
@@ -0,0 +1,184 @@
+from collections import defaultdict
+
+import intel_extension_for_pytorch as ipex
+import intel_extension_for_pytorch._C as core
+import torch
+
+OptState = ipex.cpu.autocast._grad_scaler.OptState
+_MultiDeviceReplicator = ipex.cpu.autocast._grad_scaler._MultiDeviceReplicator
+_refresh_per_optimizer_state = (
+    ipex.cpu.autocast._grad_scaler._refresh_per_optimizer_state
+)
+
+
+def _unscale_grads_(self, optimizer, inv_scale, found_inf, allow_fp16):
+    per_device_inv_scale = _MultiDeviceReplicator(inv_scale)
+    per_device_found_inf = _MultiDeviceReplicator(found_inf)
+
+    # To set up _amp_foreach_non_finite_check_and_unscale_, split grads by device and dtype.
+    # There could be hundreds of grads, so we'd like to iterate through them just once.
+    # However, we don't know their devices or dtypes in advance.
+
+    # https://stackoverflow.com/questions/5029934/defaultdict-of-defaultdict
+    # Google says mypy struggles with defaultdicts type annotations.
+    per_device_and_dtype_grads = defaultdict(lambda: defaultdict(list))  # type: ignore[var-annotated]
+    # sync grad to master weight
+    if hasattr(optimizer, "sync_grad"):
+        optimizer.sync_grad()
+    with torch.no_grad():
+        for group in optimizer.param_groups:
+            for param in group["params"]:
+                if param.grad is None:
+                    continue
+                if (not allow_fp16) and param.grad.dtype == torch.float16:
+                    raise ValueError("Attempting to unscale FP16 gradients.")
+                if param.grad.is_sparse:
+                    # is_coalesced() == False means the sparse grad has values with duplicate indices.
+                    # coalesce() deduplicates indices and adds all values that have the same index.
+                    # For scaled fp16 values, there's a good chance coalescing will cause overflow,
+                    # so we should check the coalesced _values().
+                    if param.grad.dtype is torch.float16:
+                        param.grad = param.grad.coalesce()
+                    to_unscale = param.grad._values()
+                else:
+                    to_unscale = param.grad
+
+                # -: is there a way to split by device and dtype without appending in the inner loop?
+                to_unscale = to_unscale.to("cpu")
+                per_device_and_dtype_grads[to_unscale.device][to_unscale.dtype].append(
+                    to_unscale
+                )
+
+        for _, per_dtype_grads in per_device_and_dtype_grads.items():
+            for grads in per_dtype_grads.values():
+                core._amp_foreach_non_finite_check_and_unscale_(
+                    grads,
+                    per_device_found_inf.get("cpu"),
+                    per_device_inv_scale.get("cpu"),
+                )
+
+    return per_device_found_inf._per_device_tensors
+
+
+def unscale_(self, optimizer):
+    """
+    Divides ("unscales") the optimizer's gradient tensors by the scale factor.
+    :meth:`unscale_` is optional, serving cases where you need to
+    :ref:`modify or inspect gradients<working-with-unscaled-gradients>`
+    between the backward pass(es) and :meth:`step`.
+    If :meth:`unscale_` is not called explicitly,  gradients will be unscaled  automatically during :meth:`step`.
+    Simple example, using :meth:`unscale_` to enable clipping of unscaled gradients::
+        ...
+        scaler.scale(loss).backward()
+        scaler.unscale_(optimizer)
+        torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm)
+        scaler.step(optimizer)
+        scaler.update()
+    Args:
+        optimizer (torch.optim.Optimizer):  Optimizer that owns the gradients to be unscaled.
+    .. warning::
+        :meth:`unscale_` should only be called once per optimizer per :meth:`step` call,
+        and only after all gradients for that optimizer's assigned parameters have been accumulated.
+        Calling :meth:`unscale_` twice for a given optimizer between each :meth:`step` triggers a RuntimeError.
+    .. warning::
+        :meth:`unscale_` may unscale sparse gradients out of place, replacing the ``.grad`` attribute.
+    """
+    if not self._enabled:
+        return
+
+    self._check_scale_growth_tracker("unscale_")
+
+    optimizer_state = self._per_optimizer_states[id(optimizer)]
+
+    if optimizer_state["stage"] is OptState.UNSCALED:
+        raise RuntimeError(
+            "unscale_() has already been called on this optimizer since the last update()."
+        )
+    elif optimizer_state["stage"] is OptState.STEPPED:
+        raise RuntimeError("unscale_() is being called after step().")
+
+    # FP32 division can be imprecise for certain compile options, so we carry out the reciprocal in FP64.
+    assert self._scale is not None
+    inv_scale = (
+        self._scale.to("cpu").double().reciprocal().float().to(self._scale.device)
+    )
+    found_inf = torch.full((1,), 0.0, dtype=torch.float32, device=self._scale.device)
+
+    optimizer_state["found_inf_per_device"] = self._unscale_grads_(
+        optimizer, inv_scale, found_inf, False
+    )
+    optimizer_state["stage"] = OptState.UNSCALED
+
+
+def update(self, new_scale=None):
+    """
+    Updates the scale factor.
+    If any optimizer steps were skipped the scale is multiplied by ``backoff_factor``
+    to reduce it. If ``growth_interval`` unskipped iterations occurred consecutively,
+    the scale is multiplied by ``growth_factor`` to increase it.
+    Passing ``new_scale`` sets the new scale value manually. (``new_scale`` is not
+    used directly, it's used to fill GradScaler's internal scale tensor. So if
+    ``new_scale`` was a tensor, later in-place changes to that tensor will not further
+    affect the scale GradScaler uses internally.)
+    Args:
+        new_scale (float or :class:`torch.FloatTensor`, optional, default=None):  New scale factor.
+    .. warning::
+        :meth:`update` should only be called at the end of the iteration, after ``scaler.step(optimizer)`` has
+        been invoked for all optimizers used this iteration.
+    """
+    if not self._enabled:
+        return
+
+    _scale, _growth_tracker = self._check_scale_growth_tracker("update")
+
+    if new_scale is not None:
+        # Accept a new user-defined scale.
+        if isinstance(new_scale, float):
+            self._scale.fill_(new_scale)  # type: ignore[union-attr]
+        else:
+            reason = "new_scale should be a float or a 1-element torch.FloatTensor with requires_grad=False."
+            assert isinstance(new_scale, torch.FloatTensor), reason  # type: ignore[attr-defined]
+            assert new_scale.numel() == 1, reason
+            assert new_scale.requires_grad is False, reason
+            self._scale.copy_(new_scale)  # type: ignore[union-attr]
+    else:
+        # Consume shared inf/nan data collected from optimizers to update the scale.
+        # If all found_inf tensors are on the same device as self._scale, this operation is asynchronous.
+        found_infs = [
+            found_inf.to(device="cpu", non_blocking=True)
+            for state in self._per_optimizer_states.values()
+            for found_inf in state["found_inf_per_device"].values()
+        ]
+
+        assert len(found_infs) > 0, "No inf checks were recorded prior to update."
+
+        found_inf_combined = found_infs[0]
+        if len(found_infs) > 1:
+            for i in range(1, len(found_infs)):
+                found_inf_combined += found_infs[i]
+
+        to_device = _scale.device
+        _scale = _scale.to("cpu")
+        _growth_tracker = _growth_tracker.to("cpu")
+
+        core._amp_update_scale_(
+            _scale,
+            _growth_tracker,
+            found_inf_combined,
+            self._growth_factor,
+            self._backoff_factor,
+            self._growth_interval,
+        )
+
+        _scale = _scale.to(to_device)
+        _growth_tracker = _growth_tracker.to(to_device)
+    # To prepare for next iteration, clear the data collected from optimizers this iteration.
+    self._per_optimizer_states = defaultdict(_refresh_per_optimizer_state)
+
+
+def gradscaler_init():
+    torch.xpu.amp.GradScaler = ipex.cpu.autocast._grad_scaler.GradScaler
+    torch.xpu.amp.GradScaler._unscale_grads_ = _unscale_grads_
+    torch.xpu.amp.GradScaler.unscale_ = unscale_
+    torch.xpu.amp.GradScaler.update = update
+    return torch.xpu.amp.GradScaler
diff --git a/rvc/lib/ipex/hijacks.py b/rvc/lib/ipex/hijacks.py
new file mode 100644
index 0000000000000000000000000000000000000000..f3b5afe492b068e8d5d1b37a0f28385b9c77ef40
--- /dev/null
+++ b/rvc/lib/ipex/hijacks.py
@@ -0,0 +1,352 @@
+import contextlib
+import importlib
+
+import intel_extension_for_pytorch as ipex
+import torch
+
+
+class CondFunc:
+    def __new__(cls, orig_func, sub_func, cond_func):
+        self = super(CondFunc, cls).__new__(cls)
+        if isinstance(orig_func, str):
+            func_path = orig_func.split(".")
+            for i in range(len(func_path) - 1, -1, -1):
+                try:
+                    resolved_obj = importlib.import_module(".".join(func_path[:i]))
+                    break
+                except ImportError:
+                    pass
+            for attr_name in func_path[i:-1]:
+                resolved_obj = getattr(resolved_obj, attr_name)
+            orig_func = getattr(resolved_obj, func_path[-1])
+            setattr(
+                resolved_obj,
+                func_path[-1],
+                lambda *args, **kwargs: self(*args, **kwargs),
+            )
+        self.__init__(orig_func, sub_func, cond_func)
+        return lambda *args, **kwargs: self(*args, **kwargs)
+
+    def __init__(self, orig_func, sub_func, cond_func):
+        self.__orig_func = orig_func
+        self.__sub_func = sub_func
+        self.__cond_func = cond_func
+
+    def __call__(self, *args, **kwargs):
+        if not self.__cond_func or self.__cond_func(self.__orig_func, *args, **kwargs):
+            return self.__sub_func(self.__orig_func, *args, **kwargs)
+        else:
+            return self.__orig_func(*args, **kwargs)
+
+
+_utils = torch.utils.data._utils
+
+
+def _shutdown_workers(self):
+    if (
+        torch.utils.data._utils is None
+        or torch.utils.data._utils.python_exit_status is True
+        or torch.utils.data._utils.python_exit_status is None
+    ):
+        return
+    if hasattr(self, "_shutdown") and not self._shutdown:
+        self._shutdown = True
+        try:
+            if hasattr(self, "_pin_memory_thread"):
+                self._pin_memory_thread_done_event.set()
+                self._worker_result_queue.put((None, None))
+                self._pin_memory_thread.join()
+                self._worker_result_queue.cancel_join_thread()
+                self._worker_result_queue.close()
+            self._workers_done_event.set()
+            for worker_id in range(len(self._workers)):
+                if self._persistent_workers or self._workers_status[worker_id]:
+                    self._mark_worker_as_unavailable(worker_id, shutdown=True)
+            for w in self._workers:
+                w.join(timeout=torch.utils.data._utils.MP_STATUS_CHECK_INTERVAL)
+            for q in self._index_queues:
+                q.cancel_join_thread()
+                q.close()
+        finally:
+            if self._worker_pids_set:
+                torch.utils.data._utils.signal_handling._remove_worker_pids(id(self))
+                self._worker_pids_set = False
+            for w in self._workers:
+                if w.is_alive():
+                    w.terminate()
+
+
+class DummyDataParallel(torch.nn.Module):
+    def __new__(cls, module, device_ids=None, output_device=None, dim=0):
+        if isinstance(device_ids, list) and len(device_ids) > 1:
+            print("IPEX backend doesn't support DataParallel on multiple XPU devices")
+        return module.to("xpu")
+
+
+def return_null_context(*args, **kwargs):
+    return contextlib.nullcontext()
+
+
+def check_device(device):
+    return bool(
+        (isinstance(device, torch.device) and device.type == "cuda")
+        or (isinstance(device, str) and "cuda" in device)
+        or isinstance(device, int)
+    )
+
+
+def return_xpu(device):
+    return (
+        f"xpu:{device[-1]}"
+        if isinstance(device, str) and ":" in device
+        else f"xpu:{device}"
+        if isinstance(device, int)
+        else torch.device("xpu")
+        if isinstance(device, torch.device)
+        else "xpu"
+    )
+
+
+def ipex_no_cuda(orig_func, *args, **kwargs):
+    torch.cuda.is_available = lambda: False
+    orig_func(*args, **kwargs)
+    torch.cuda.is_available = torch.xpu.is_available
+
+
+original_autocast = torch.autocast
+
+
+def ipex_autocast(*args, **kwargs):
+    if len(args) > 0 and args[0] == "cuda":
+        return original_autocast("xpu", *args[1:], **kwargs)
+    else:
+        return original_autocast(*args, **kwargs)
+
+
+original_torch_cat = torch.cat
+
+
+def torch_cat(tensor, *args, **kwargs):
+    if len(tensor) == 3 and (
+        tensor[0].dtype != tensor[1].dtype or tensor[2].dtype != tensor[1].dtype
+    ):
+        return original_torch_cat(
+            [tensor[0].to(tensor[1].dtype), tensor[1], tensor[2].to(tensor[1].dtype)],
+            *args,
+            **kwargs,
+        )
+    else:
+        return original_torch_cat(tensor, *args, **kwargs)
+
+
+original_interpolate = torch.nn.functional.interpolate
+
+
+def interpolate(
+    tensor,
+    size=None,
+    scale_factor=None,
+    mode="nearest",
+    align_corners=None,
+    recompute_scale_factor=None,
+    antialias=False,
+):
+    if antialias or align_corners is not None:
+        return_device = tensor.device
+        return_dtype = tensor.dtype
+        return original_interpolate(
+            tensor.to("cpu", dtype=torch.float32),
+            size=size,
+            scale_factor=scale_factor,
+            mode=mode,
+            align_corners=align_corners,
+            recompute_scale_factor=recompute_scale_factor,
+            antialias=antialias,
+        ).to(return_device, dtype=return_dtype)
+    else:
+        return original_interpolate(
+            tensor,
+            size=size,
+            scale_factor=scale_factor,
+            mode=mode,
+            align_corners=align_corners,
+            recompute_scale_factor=recompute_scale_factor,
+            antialias=antialias,
+        )
+
+
+original_linalg_solve = torch.linalg.solve
+
+
+def linalg_solve(A, B, *args, **kwargs):
+    if A.device != torch.device("cpu") or B.device != torch.device("cpu"):
+        return_device = A.device
+        return original_linalg_solve(A.to("cpu"), B.to("cpu"), *args, **kwargs).to(
+            return_device
+        )
+    else:
+        return original_linalg_solve(A, B, *args, **kwargs)
+
+
+def ipex_hijacks():
+    CondFunc(
+        "torch.Tensor.to",
+        lambda orig_func, self, device=None, *args, **kwargs: orig_func(
+            self, return_xpu(device), *args, **kwargs
+        ),
+        lambda orig_func, self, device=None, *args, **kwargs: check_device(device),
+    )
+    CondFunc(
+        "torch.Tensor.cuda",
+        lambda orig_func, self, device=None, *args, **kwargs: orig_func(
+            self, return_xpu(device), *args, **kwargs
+        ),
+        lambda orig_func, self, device=None, *args, **kwargs: check_device(device),
+    )
+    CondFunc(
+        "torch.empty",
+        lambda orig_func, *args, device=None, **kwargs: orig_func(
+            *args, device=return_xpu(device), **kwargs
+        ),
+        lambda orig_func, *args, device=None, **kwargs: check_device(device),
+    )
+    CondFunc(
+        "torch.load",
+        lambda orig_func, *args, map_location=None, **kwargs: orig_func(
+            *args, return_xpu(map_location), **kwargs
+        ),
+        lambda orig_func, *args, map_location=None, **kwargs: map_location is None
+        or check_device(map_location),
+    )
+    CondFunc(
+        "torch.randn",
+        lambda orig_func, *args, device=None, **kwargs: orig_func(
+            *args, device=return_xpu(device), **kwargs
+        ),
+        lambda orig_func, *args, device=None, **kwargs: check_device(device),
+    )
+    CondFunc(
+        "torch.ones",
+        lambda orig_func, *args, device=None, **kwargs: orig_func(
+            *args, device=return_xpu(device), **kwargs
+        ),
+        lambda orig_func, *args, device=None, **kwargs: check_device(device),
+    )
+    CondFunc(
+        "torch.zeros",
+        lambda orig_func, *args, device=None, **kwargs: orig_func(
+            *args, device=return_xpu(device), **kwargs
+        ),
+        lambda orig_func, *args, device=None, **kwargs: check_device(device),
+    )
+    CondFunc(
+        "torch.tensor",
+        lambda orig_func, *args, device=None, **kwargs: orig_func(
+            *args, device=return_xpu(device), **kwargs
+        ),
+        lambda orig_func, *args, device=None, **kwargs: check_device(device),
+    )
+    CondFunc(
+        "torch.linspace",
+        lambda orig_func, *args, device=None, **kwargs: orig_func(
+            *args, device=return_xpu(device), **kwargs
+        ),
+        lambda orig_func, *args, device=None, **kwargs: check_device(device),
+    )
+
+    CondFunc(
+        "torch.Generator",
+        lambda orig_func, device=None: torch.xpu.Generator(device),
+        lambda orig_func, device=None: device is not None
+        and device != torch.device("cpu")
+        and device != "cpu",
+    )
+
+    CondFunc(
+        "torch.batch_norm",
+        lambda orig_func, input, weight, bias, *args, **kwargs: orig_func(
+            input,
+            weight
+            if weight is not None
+            else torch.ones(input.size()[1], device=input.device),
+            bias
+            if bias is not None
+            else torch.zeros(input.size()[1], device=input.device),
+            *args,
+            **kwargs,
+        ),
+        lambda orig_func, input, *args, **kwargs: input.device != torch.device("cpu"),
+    )
+    CondFunc(
+        "torch.instance_norm",
+        lambda orig_func, input, weight, bias, *args, **kwargs: orig_func(
+            input,
+            weight
+            if weight is not None
+            else torch.ones(input.size()[1], device=input.device),
+            bias
+            if bias is not None
+            else torch.zeros(input.size()[1], device=input.device),
+            *args,
+            **kwargs,
+        ),
+        lambda orig_func, input, *args, **kwargs: input.device != torch.device("cpu"),
+    )
+
+    # Functions with dtype errors:
+    CondFunc(
+        "torch.nn.modules.GroupNorm.forward",
+        lambda orig_func, self, input: orig_func(
+            self, input.to(self.weight.data.dtype)
+        ),
+        lambda orig_func, self, input: input.dtype != self.weight.data.dtype,
+    )
+    CondFunc(
+        "torch.nn.modules.linear.Linear.forward",
+        lambda orig_func, self, input: orig_func(
+            self, input.to(self.weight.data.dtype)
+        ),
+        lambda orig_func, self, input: input.dtype != self.weight.data.dtype,
+    )
+    CondFunc(
+        "torch.nn.modules.conv.Conv2d.forward",
+        lambda orig_func, self, input: orig_func(
+            self, input.to(self.weight.data.dtype)
+        ),
+        lambda orig_func, self, input: input.dtype != self.weight.data.dtype,
+    )
+    CondFunc(
+        "torch.nn.functional.layer_norm",
+        lambda orig_func, input, normalized_shape=None, weight=None, *args, **kwargs: orig_func(
+            input.to(weight.data.dtype), normalized_shape, weight, *args, **kwargs
+        ),
+        lambda orig_func, input, normalized_shape=None, weight=None, *args, **kwargs: weight
+        is not None
+        and input.dtype != weight.data.dtype,
+    )
+
+    # Diffusers Float64 (ARC GPUs doesn't support double or Float64):
+    if not torch.xpu.has_fp64_dtype():
+        CondFunc(
+            "torch.from_numpy",
+            lambda orig_func, ndarray: orig_func(ndarray.astype("float32")),
+            lambda orig_func, ndarray: ndarray.dtype == float,
+        )
+
+    # Broken functions when torch.cuda.is_available is True:
+    CondFunc(
+        "torch.utils.data.dataloader._BaseDataLoaderIter.__init__",
+        lambda orig_func, *args, **kwargs: ipex_no_cuda(orig_func, *args, **kwargs),
+        lambda orig_func, *args, **kwargs: True,
+    )
+
+    # Functions that make compile mad with CondFunc:
+    torch.utils.data.dataloader._MultiProcessingDataLoaderIter._shutdown_workers = (
+        _shutdown_workers
+    )
+    torch.nn.DataParallel = DummyDataParallel
+    torch.autocast = ipex_autocast
+    torch.cat = torch_cat
+    torch.linalg.solve = linalg_solve
+    torch.nn.functional.interpolate = interpolate
+    torch.backends.cuda.sdp_kernel = return_null_context
diff --git a/rvc/lib/jit/__init__.py b/rvc/lib/jit/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..03950d36f010995cf0939485c91095b8a82dc829
--- /dev/null
+++ b/rvc/lib/jit/__init__.py
@@ -0,0 +1,164 @@
+import pickle
+import time
+from collections import OrderedDict
+from io import BytesIO
+
+import torch
+from tqdm import tqdm
+
+
+def load_inputs(path, device, is_half=False):
+    parm = torch.load(path, map_location=torch.device("cpu"))
+    for key in parm.keys():
+        parm[key] = parm[key].to(device)
+        if is_half and parm[key].dtype == torch.float32:
+            parm[key] = parm[key].half()
+        elif not is_half and parm[key].dtype == torch.float16:
+            parm[key] = parm[key].float()
+    return parm
+
+
+def benchmark(
+    model, inputs_path, device=torch.device("cpu"), epoch=1000, is_half=False
+):
+    parm = load_inputs(inputs_path, device, is_half)
+    total_ts = 0.0
+    bar = tqdm(range(epoch))
+    for i in bar:
+        start_time = time.perf_counter()
+        o = model(**parm)
+        total_ts += time.perf_counter() - start_time
+    print(f"num_epoch: {epoch} | avg time(ms): {(total_ts*1000)/epoch}")
+
+
+def jit_warm_up(model, inputs_path, device=torch.device("cpu"), epoch=5, is_half=False):
+    benchmark(model, inputs_path, device, epoch=epoch, is_half=is_half)
+
+
+def to_jit_model(
+    model_path,
+    model_type: str,
+    mode: str = "trace",
+    inputs_path: str = None,
+    device=torch.device("cpu"),
+    is_half=False,
+):
+    model = None
+    if model_type.lower() == "synthesizer":
+        from .get_synthesizer import get_synthesizer
+
+        model, _ = get_synthesizer(model_path, device)
+        model.forward = model.infer
+    elif model_type.lower() == "rmvpe":
+        from .get_rmvpe import get_rmvpe
+
+        model = get_rmvpe(model_path, device)
+    elif model_type.lower() == "hubert":
+        from .get_hubert import get_hubert_model
+
+        model = get_hubert_model(model_path, device)
+        model.forward = model.infer
+    else:
+        raise ValueError(f"No model type named {model_type}")
+    model = model.eval()
+    model = model.half() if is_half else model.float()
+    if mode == "trace":
+        assert not inputs_path
+        inputs = load_inputs(inputs_path, device, is_half)
+        model_jit = torch.jit.trace(model, example_kwarg_inputs=inputs)
+    elif mode == "script":
+        model_jit = torch.jit.script(model)
+    model_jit.to(device)
+    model_jit = model_jit.half() if is_half else model_jit.float()
+    # model = model.half() if is_half else model.float()
+    return (model, model_jit)
+
+
+def export(
+    model: torch.nn.Module,
+    mode: str = "trace",
+    inputs: dict = None,
+    device=torch.device("cpu"),
+    is_half: bool = False,
+) -> dict:
+    model = model.half() if is_half else model.float()
+    model.eval()
+    if mode == "trace":
+        assert inputs is not None
+        model_jit = torch.jit.trace(model, example_kwarg_inputs=inputs)
+    elif mode == "script":
+        model_jit = torch.jit.script(model)
+    model_jit.to(device)
+    model_jit = model_jit.half() if is_half else model_jit.float()
+    buffer = BytesIO()
+    # model_jit=model_jit.cpu()
+    torch.jit.save(model_jit, buffer)
+    del model_jit
+    cpt = OrderedDict()
+    cpt["model"] = buffer.getvalue()
+    cpt["is_half"] = is_half
+    return cpt
+
+
+def load(path: str):
+    with open(path, "rb") as f:
+        return pickle.load(f)
+
+
+def save(ckpt: dict, save_path: str):
+    with open(save_path, "wb") as f:
+        pickle.dump(ckpt, f)
+
+
+def rmvpe_jit_export(
+    model_path: str,
+    mode: str = "script",
+    inputs_path: str = None,
+    save_path: str = None,
+    device=torch.device("cpu"),
+    is_half=False,
+):
+    if not save_path:
+        save_path = model_path.rstrip(".pth")
+        save_path += ".half.jit" if is_half else ".jit"
+    if "cuda" in str(device) and ":" not in str(device):
+        device = torch.device("cuda:0")
+    from .get_rmvpe import get_rmvpe
+
+    model = get_rmvpe(model_path, device)
+    inputs = None
+    if mode == "trace":
+        inputs = load_inputs(inputs_path, device, is_half)
+    ckpt = export(model, mode, inputs, device, is_half)
+    ckpt["device"] = str(device)
+    save(ckpt, save_path)
+    return ckpt
+
+
+def synthesizer_jit_export(
+    model_path: str,
+    mode: str = "script",
+    inputs_path: str = None,
+    save_path: str = None,
+    device=torch.device("cpu"),
+    is_half=False,
+):
+    if not save_path:
+        save_path = model_path.rstrip(".pth")
+        save_path += ".half.jit" if is_half else ".jit"
+    if "cuda" in str(device) and ":" not in str(device):
+        device = torch.device("cuda:0")
+    from .get_synthesizer import get_synthesizer
+
+    model, cpt = get_synthesizer(model_path, device)
+    assert isinstance(cpt, dict)
+    model.forward = model.infer
+    inputs = None
+    if mode == "trace":
+        inputs = load_inputs(inputs_path, device, is_half)
+    ckpt = export(model, mode, inputs, device, is_half)
+    cpt.pop("weight")
+    cpt["model"] = ckpt["model"]
+    cpt["device"] = device
+    save(cpt, save_path)
+    return cpt
diff --git a/rvc/lib/jit/get_hubert.py b/rvc/lib/jit/get_hubert.py
new file mode 100644
index 0000000000000000000000000000000000000000..a073f7421ae528aba53b0587fe90467600e393bb
--- /dev/null
+++ b/rvc/lib/jit/get_hubert.py
@@ -0,0 +1,343 @@
+import math
+import random
+from typing import Optional, Tuple
+
+import numpy as np
+import torch
+import torch.nn.functional as F
+from fairseq.checkpoint_utils import load_model_ensemble_and_task
+
+# from fairseq.data.data_utils import compute_mask_indices
+from fairseq.utils import index_put
+
+
+# @torch.jit.script
+def pad_to_multiple(x, multiple, dim=-1, value=0):
+    # Inspired from https://github.com/lucidrains/local-attention/blob/master/local_attention/local_attention.py#L41
+    if x is None:
+        return None, 0
+    tsz = x.size(dim)
+    m = tsz / multiple
+    remainder = math.ceil(m) * multiple - tsz
+    if int(tsz % multiple) == 0:
+        return x, 0
+    pad_offset = (0,) * (-1 - dim) * 2
+
+    return F.pad(x, (*pad_offset, 0, remainder), value=value), remainder
+
+
+def extract_features(
+    self,
+    x,
+    padding_mask=None,
+    tgt_layer=None,
+    min_layer=0,
+):
+    if padding_mask is not None:
+        x = index_put(x, padding_mask, 0)
+
+    x_conv = self.pos_conv(x.transpose(1, 2))
+    x_conv = x_conv.transpose(1, 2)
+    x = x + x_conv
+
+    if not self.layer_norm_first:
+        x = self.layer_norm(x)
+
+    # pad to the sequence length dimension
+    x, pad_length = pad_to_multiple(x, self.required_seq_len_multiple, dim=-2, value=0)
+    if pad_length > 0 and padding_mask is None:
+        padding_mask = x.new_zeros((x.size(0), x.size(1)), dtype=torch.bool)
+        padding_mask[:, -pad_length:] = True
+    else:
+        padding_mask, _ = pad_to_multiple(
+            padding_mask, self.required_seq_len_multiple, dim=-1, value=True
+        )
+    x = F.dropout(x, p=self.dropout, training=self.training)
+
+    # B x T x C -> T x B x C
+    x = x.transpose(0, 1)
+
+    layer_results = []
+    r = None
+    for i, layer in enumerate(self.layers):
+        dropout_probability = np.random.random() if self.layerdrop > 0 else 1
+        if not self.training or (dropout_probability > self.layerdrop):
+            x, (z, lr) = layer(
+                x, self_attn_padding_mask=padding_mask, need_weights=False
+            )
+            if i >= min_layer:
+                layer_results.append((x, z, lr))
+        if i == tgt_layer:
+            r = x
+            break
+
+    if r is not None:
+        x = r
+
+    # T x B x C -> B x T x C
+    x = x.transpose(0, 1)
+
+    # undo paddding
+    if pad_length > 0:
+        x = x[:, :-pad_length]
+
+        def undo_pad(a, b, c):
+            return (
+                a[:-pad_length],
+                b[:-pad_length] if b is not None else b,
+                c[:-pad_length],
+            )
+
+        layer_results = [undo_pad(*u) for u in layer_results]
+
+    return x, layer_results
+
+
+def compute_mask_indices(
+    shape: Tuple[int, int],
+    padding_mask: Optional[torch.Tensor],
+    mask_prob: float,
+    mask_length: int,
+    mask_type: str = "static",
+    mask_other: float = 0.0,
+    min_masks: int = 0,
+    no_overlap: bool = False,
+    min_space: int = 0,
+    require_same_masks: bool = True,
+    mask_dropout: float = 0.0,
+) -> torch.Tensor:
+    """
+    Computes random mask spans for a given shape
+
+    Args:
+        shape: the the shape for which to compute masks.
+            should be of size 2 where first element is batch size and 2nd is timesteps
+        padding_mask: optional padding mask of the same size as shape, which will prevent masking padded elements
+        mask_prob: probability for each token to be chosen as start of the span to be masked. this will be multiplied by
+            number of timesteps divided by length of mask span to mask approximately this percentage of all elements.
+            however due to overlaps, the actual number will be smaller (unless no_overlap is True)
+        mask_type: how to compute mask lengths
+            static = fixed size
+            uniform = sample from uniform distribution [mask_other, mask_length*2]
+            normal = sample from normal distribution with mean mask_length and stdev mask_other. mask is min 1 element
+            poisson = sample from possion distribution with lambda = mask length
+        min_masks: minimum number of masked spans
+        no_overlap: if false, will switch to an alternative recursive algorithm that prevents spans from overlapping
+        min_space: only used if no_overlap is True, this is how many elements to keep unmasked between spans
+        require_same_masks: if true, will randomly drop out masks until same amount of masks remains in each sample
+        mask_dropout: randomly dropout this percentage of masks in each example
+    """
+
+    bsz, all_sz = shape
+    mask = torch.full((bsz, all_sz), False)
+
+    all_num_mask = int(
+        # add a random number for probabilistic rounding
+        mask_prob * all_sz / float(mask_length)
+        + torch.rand([1]).item()
+    )
+
+    all_num_mask = max(min_masks, all_num_mask)
+
+    mask_idcs = []
+    for i in range(bsz):
+        if padding_mask is not None:
+            sz = all_sz - padding_mask[i].long().sum().item()
+            num_mask = int(mask_prob * sz / float(mask_length) + np.random.rand())
+            num_mask = max(min_masks, num_mask)
+        else:
+            sz = all_sz
+            num_mask = all_num_mask
+
+        if mask_type == "static":
+            lengths = torch.full([num_mask], mask_length)
+        elif mask_type == "uniform":
+            lengths = torch.randint(mask_other, mask_length * 2 + 1, size=[num_mask])
+        elif mask_type == "normal":
+            lengths = torch.normal(mask_length, mask_other, size=[num_mask])
+            lengths = [max(1, int(round(x))) for x in lengths]
+        else:
+            raise Exception("unknown mask selection " + mask_type)
+
+        if sum(lengths) == 0:
+            lengths[0] = min(mask_length, sz - 1)
+
+        if no_overlap:
+            mask_idc = []
+
+            def arrange(s, e, length, keep_length):
+                span_start = torch.randint(low=s, high=e - length, size=[1]).item()
+                mask_idc.extend(span_start + i for i in range(length))
+
+                new_parts = []
+                if span_start - s - min_space >= keep_length:
+                    new_parts.append((s, span_start - min_space + 1))
+                if e - span_start - length - min_space > keep_length:
+                    new_parts.append((span_start + length + min_space, e))
+                return new_parts
+
+            parts = [(0, sz)]
+            min_length = min(lengths)
+            for length in sorted(lengths, reverse=True):
+                t = [e - s if e - s >= length + min_space else 0 for s, e in parts]
+                lens = torch.asarray(t, dtype=torch.int)
+                l_sum = torch.sum(lens)
+                if l_sum == 0:
+                    break
+                probs = lens / torch.sum(lens)
+                c = torch.multinomial(probs.float(), len(parts)).item()
+                s, e = parts.pop(c)
+                parts.extend(arrange(s, e, length, min_length))
+            mask_idc = torch.asarray(mask_idc)
+        else:
+            min_len = min(lengths)
+            if sz - min_len <= num_mask:
+                min_len = sz - num_mask - 1
+            mask_idc = torch.asarray(
+                random.sample([i for i in range(sz - min_len)], num_mask)
+            )
+            mask_idc = torch.asarray(
+                [
+                    mask_idc[j] + offset
+                    for j in range(len(mask_idc))
+                    for offset in range(lengths[j])
+                ]
+            )
+
+        mask_idcs.append(torch.unique(mask_idc[mask_idc < sz]))
+
+    min_len = min([len(m) for m in mask_idcs])
+    for i, mask_idc in enumerate(mask_idcs):
+        if isinstance(mask_idc, torch.Tensor):
+            mask_idc = torch.asarray(mask_idc, dtype=torch.float)
+        if len(mask_idc) > min_len and require_same_masks:
+            mask_idc = torch.asarray(
+                random.sample([i for i in range(mask_idc)], min_len)
+            )
+        if mask_dropout > 0:
+            num_holes = int(round(len(mask_idc) * mask_dropout))
+            mask_idc = torch.asarray(
+                random.sample([i for i in range(mask_idc)], len(mask_idc) - num_holes)
+            )
+
+        mask[i, mask_idc.int()] = True
+
+    return mask
+
+
+def apply_mask(self, x, padding_mask, target_list):
+    B, T, C = x.shape
+    torch.zeros_like(x)
+    if self.mask_prob > 0:
+        mask_indices = compute_mask_indices(
+            (B, T),
+            padding_mask,
+            self.mask_prob,
+            self.mask_length,
+            self.mask_selection,
+            self.mask_other,
+            min_masks=2,
+            no_overlap=self.no_mask_overlap,
+            min_space=self.mask_min_space,
+        )
+        mask_indices = mask_indices.to(x.device)
+        x[mask_indices] = self.mask_emb
+    else:
+        mask_indices = None
+
+    if self.mask_channel_prob > 0:
+        mask_channel_indices = compute_mask_indices(
+            (B, C),
+            None,
+            self.mask_channel_prob,
+            self.mask_channel_length,
+            self.mask_channel_selection,
+            self.mask_channel_other,
+            no_overlap=self.no_mask_channel_overlap,
+            min_space=self.mask_channel_min_space,
+        )
+        mask_channel_indices = (
+            mask_channel_indices.to(x.device).unsqueeze(1).expand(-1, T, -1)
+        )
+        x[mask_channel_indices] = 0
+
+    return x, mask_indices
+
+
+def get_hubert_model(
+    model_path="assets/hubert/hubert_base.pt", device=torch.device("cpu")
+):
+    models, _, _ = load_model_ensemble_and_task(
+        [model_path],
+        suffix="",
+    )
+    hubert_model = models[0]
+    hubert_model = hubert_model.to(device)
+
+    def _apply_mask(x, padding_mask, target_list):
+        return apply_mask(hubert_model, x, padding_mask, target_list)
+
+    hubert_model.apply_mask = _apply_mask
+
+    def _extract_features(
+        x,
+        padding_mask=None,
+        tgt_layer=None,
+        min_layer=0,
+    ):
+        return extract_features(
+            hubert_model.encoder,
+            x,
+            padding_mask=padding_mask,
+            tgt_layer=tgt_layer,
+            min_layer=min_layer,
+        )
+
+    hubert_model.encoder.extract_features = _extract_features
+
+    hubert_model._forward = hubert_model.forward
+
+    def hubert_extract_features(
+        self,
+        source: torch.Tensor,
+        padding_mask: Optional[torch.Tensor] = None,
+        mask: bool = False,
+        ret_conv: bool = False,
+        output_layer: Optional[int] = None,
+    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        res = self._forward(
+            source,
+            padding_mask=padding_mask,
+            mask=mask,
+            features_only=True,
+            output_layer=output_layer,
+        )
+        feature = res["features"] if ret_conv else res["x"]
+        return feature, res["padding_mask"]
+
+    def _hubert_extract_features(
+        source: torch.Tensor,
+        padding_mask: Optional[torch.Tensor] = None,
+        mask: bool = False,
+        ret_conv: bool = False,
+        output_layer: Optional[int] = None,
+    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        return hubert_extract_features(
+            hubert_model, source, padding_mask, mask, ret_conv, output_layer
+        )
+
+    hubert_model.extract_features = _hubert_extract_features
+
+    def infer(source, padding_mask, output_layer: torch.Tensor):
+        output_layer = output_layer.item()
+        logits = hubert_model.extract_features(
+            source=source, padding_mask=padding_mask, output_layer=output_layer
+        )
+        feats = hubert_model.final_proj(logits[0]) if output_layer == 9 else logits[0]
+        return feats
+
+    hubert_model.infer = infer
+    # hubert_model.forward=infer
+    # hubert_model.forward
+
+    return hubert_model
diff --git a/rvc/lib/jit/get_rmvpe.py b/rvc/lib/jit/get_rmvpe.py
new file mode 100644
index 0000000000000000000000000000000000000000..e71c39fb0275d3891690af72b6f7e8dd11b00f70
--- /dev/null
+++ b/rvc/lib/jit/get_rmvpe.py
@@ -0,0 +1,12 @@
+import torch
+
+
+def get_rmvpe(model_path="assets/rmvpe/rmvpe.pt", device=torch.device("cpu")):
+    from infer.lib.rmvpe import E2E
+
+    model = E2E(4, 1, (2, 2))
+    ckpt = torch.load(model_path, map_location=device)
+    model.load_state_dict(ckpt)
+    model.eval()
+    model = model.to(device)
+    return model
diff --git a/rvc/lib/jit/get_synthesizer.py b/rvc/lib/jit/get_synthesizer.py
new file mode 100644
index 0000000000000000000000000000000000000000..ef5fe58b303b1d46533d8b7181f6231012dd5dbd
--- /dev/null
+++ b/rvc/lib/jit/get_synthesizer.py
@@ -0,0 +1,37 @@
+import torch
+
+
+def get_synthesizer(pth_path, device=torch.device("cpu")):
+    from infer.lib.infer_pack.models import (
+        SynthesizerTrnMs256NSFsid,
+        SynthesizerTrnMs256NSFsid_nono,
+        SynthesizerTrnMs768NSFsid,
+        SynthesizerTrnMs768NSFsid_nono,
+    )
+
+    cpt = torch.load(pth_path, map_location=torch.device("cpu"))
+    # tgt_sr = cpt["config"][-1]
+    cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0]
+    if_f0 = cpt.get("f0", 1)
+    version = cpt.get("version", "v1")
+    if version == "v1":
+        if if_f0 == 1:
+            net_g = SynthesizerTrnMs256NSFsid(*cpt["config"], is_half=False)
+        else:
+            net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
+    elif version == "v2":
+        if if_f0 == 1:
+            net_g = SynthesizerTrnMs768NSFsid(*cpt["config"], is_half=False)
+        else:
+            net_g = SynthesizerTrnMs768NSFsid_nono(*cpt["config"])
+    del net_g.enc_q
+    # net_g.forward = net_g.infer
+    # ckpt = {}
+    # ckpt["config"] = cpt["config"]
+    # ckpt["f0"] = if_f0
+    # ckpt["version"] = version
+    # ckpt["info"] = cpt.get("info", "0epoch")
+    net_g.load_state_dict(cpt["weight"], strict=False)
+    net_g = net_g.float()
+    net_g.eval().to(device)
+    return net_g, cpt
diff --git a/rvc/lib/rmvpe.py b/rvc/lib/rmvpe.py
new file mode 100644
index 0000000000000000000000000000000000000000..27f728d70bd53bc5a07247e266cbef2ac025d050
--- /dev/null
+++ b/rvc/lib/rmvpe.py
@@ -0,0 +1,665 @@
+import os
+from io import BytesIO
+from typing import List, Optional, Tuple
+
+import numpy as np
+import torch
+
+from rvc.lib import jit
+
+try:
+    # Fix "Torch not compiled with CUDA enabled"
+    import intel_extension_for_pytorch as ipex  # pylint: disable=import-error, unused-import
+
+    if torch.xpu.is_available():
+        from rvc.lib.ipex import ipex_init
+
+        ipex_init()
+except Exception:  # pylint: disable=broad-exception-caught
+    pass
+import logging
+from time import time as ttime
+
+import torch.nn as nn
+import torch.nn.functional as F
+from librosa.filters import mel
+from librosa.util import normalize, pad_center, tiny
+from scipy.signal import get_window
+
+logger = logging.getLogger(__name__)
+
+
+class STFT(torch.nn.Module):
+    def __init__(
+        self, filter_length=1024, hop_length=512, win_length=None, window="hann"
+    ):
+        """
+        This module implements an STFT using 1D convolution and 1D transpose convolutions.
+        This is a bit tricky so there are some cases that probably won't work as working
+        out the same sizes before and after in all overlap add setups is tough. Right now,
+        this code should work with hop lengths that are half the filter length (50% overlap
+        between frames).
+
+        Keyword Arguments:
+            filter_length {int} -- Length of filters used (default: {1024})
+            hop_length {int} -- Hop length of STFT (restrict to 50% overlap between frames) (default: {512})
+            win_length {[type]} -- Length of the window function applied to each frame (if not specified, it
+                equals the filter length). (default: {None})
+            window {str} -- Type of window to use (options are bartlett, hann, hamming, blackman, blackmanharris)
+                (default: {'hann'})
+        """
+        super(STFT, self).__init__()
+        self.filter_length = filter_length
+        self.hop_length = hop_length
+        self.win_length = win_length if win_length else filter_length
+        self.window = window
+        self.forward_transform = None
+        self.pad_amount = int(self.filter_length / 2)
+        fourier_basis = np.fft.fft(np.eye(self.filter_length))
+
+        cutoff = int((self.filter_length / 2 + 1))
+        fourier_basis = np.vstack(
+            [np.real(fourier_basis[:cutoff, :]), np.imag(fourier_basis[:cutoff, :])]
+        )
+        forward_basis = torch.FloatTensor(fourier_basis)
+        inverse_basis = torch.FloatTensor(np.linalg.pinv(fourier_basis))
+
+        assert filter_length >= self.win_length
+        # get window and zero center pad it to filter_length
+        fft_window = get_window(window, self.win_length, fftbins=True)
+        fft_window = pad_center(fft_window, size=filter_length)
+        fft_window = torch.from_numpy(fft_window).float()
+
+        # window the bases
+        forward_basis *= fft_window
+        inverse_basis = (inverse_basis.T * fft_window).T
+
+        self.register_buffer("forward_basis", forward_basis.float())
+        self.register_buffer("inverse_basis", inverse_basis.float())
+        self.register_buffer("fft_window", fft_window.float())
+
+    def transform(self, input_data, return_phase=False):
+        """Take input data (audio) to STFT domain.
+
+        Arguments:
+            input_data {tensor} -- Tensor of floats, with shape (num_batch, num_samples)
+
+        Returns:
+            magnitude {tensor} -- Magnitude of STFT with shape (num_batch,
+                num_frequencies, num_frames)
+            phase {tensor} -- Phase of STFT with shape (num_batch,
+                num_frequencies, num_frames)
+        """
+        input_data = F.pad(
+            input_data,
+            (self.pad_amount, self.pad_amount),
+            mode="reflect",
+        )
+        forward_transform = input_data.unfold(
+            1, self.filter_length, self.hop_length
+        ).permute(0, 2, 1)
+        forward_transform = torch.matmul(self.forward_basis, forward_transform)
+        cutoff = int((self.filter_length / 2) + 1)
+        real_part = forward_transform[:, :cutoff, :]
+        imag_part = forward_transform[:, cutoff:, :]
+        magnitude = torch.sqrt(real_part**2 + imag_part**2)
+        if return_phase:
+            phase = torch.atan2(imag_part.data, real_part.data)
+            return magnitude, phase
+        else:
+            return magnitude
+
+    def inverse(self, magnitude, phase):
+        """Call the inverse STFT (iSTFT), given magnitude and phase tensors produced
+        by the ```transform``` function.
+
+        Arguments:
+            magnitude {tensor} -- Magnitude of STFT with shape (num_batch,
+                num_frequencies, num_frames)
+            phase {tensor} -- Phase of STFT with shape (num_batch,
+                num_frequencies, num_frames)
+
+        Returns:
+            inverse_transform {tensor} -- Reconstructed audio given magnitude and phase. Of
+                shape (num_batch, num_samples)
+        """
+        cat = torch.cat(
+            [magnitude * torch.cos(phase), magnitude * torch.sin(phase)], dim=1
+        )
+        fold = torch.nn.Fold(
+            output_size=(1, (cat.size(-1) - 1) * self.hop_length + self.filter_length),
+            kernel_size=(1, self.filter_length),
+            stride=(1, self.hop_length),
+        )
+        inverse_transform = torch.matmul(self.inverse_basis, cat)
+        inverse_transform = fold(inverse_transform)[
+            :, 0, 0, self.pad_amount : -self.pad_amount
+        ]
+        window_square_sum = (
+            self.fft_window.pow(2).repeat(cat.size(-1), 1).T.unsqueeze(0)
+        )
+        window_square_sum = fold(window_square_sum)[
+            :, 0, 0, self.pad_amount : -self.pad_amount
+        ]
+        inverse_transform /= window_square_sum
+        return inverse_transform
+
+    def forward(self, input_data):
+        """Take input data (audio) to STFT domain and then back to audio.
+
+        Arguments:
+            input_data {tensor} -- Tensor of floats, with shape (num_batch, num_samples)
+
+        Returns:
+            reconstruction {tensor} -- Reconstructed audio given magnitude and phase. Of
+                shape (num_batch, num_samples)
+        """
+        self.magnitude, self.phase = self.transform(input_data, return_phase=True)
+        reconstruction = self.inverse(self.magnitude, self.phase)
+        return reconstruction
+
+
+class BiGRU(nn.Module):
+    def __init__(self, input_features, hidden_features, num_layers):
+        super(BiGRU, self).__init__()
+        self.gru = nn.GRU(
+            input_features,
+            hidden_features,
+            num_layers=num_layers,
+            batch_first=True,
+            bidirectional=True,
+        )
+
+    def forward(self, x):
+        return self.gru(x)[0]
+
+
+class ConvBlockRes(nn.Module):
+    def __init__(self, in_channels, out_channels, momentum=0.01):
+        super(ConvBlockRes, self).__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(
+                in_channels=in_channels,
+                out_channels=out_channels,
+                kernel_size=(3, 3),
+                stride=(1, 1),
+                padding=(1, 1),
+                bias=False,
+            ),
+            nn.BatchNorm2d(out_channels, momentum=momentum),
+            nn.ReLU(),
+            nn.Conv2d(
+                in_channels=out_channels,
+                out_channels=out_channels,
+                kernel_size=(3, 3),
+                stride=(1, 1),
+                padding=(1, 1),
+                bias=False,
+            ),
+            nn.BatchNorm2d(out_channels, momentum=momentum),
+            nn.ReLU(),
+        )
+        # self.shortcut:Optional[nn.Module] = None
+        if in_channels != out_channels:
+            self.shortcut = nn.Conv2d(in_channels, out_channels, (1, 1))
+
+    def forward(self, x: torch.Tensor):
+        if not hasattr(self, "shortcut"):
+            return self.conv(x) + x
+        else:
+            return self.conv(x) + self.shortcut(x)
+
+
+class Encoder(nn.Module):
+    def __init__(
+        self,
+        in_channels,
+        in_size,
+        n_encoders,
+        kernel_size,
+        n_blocks,
+        out_channels=16,
+        momentum=0.01,
+    ):
+        super(Encoder, self).__init__()
+        self.n_encoders = n_encoders
+        self.bn = nn.BatchNorm2d(in_channels, momentum=momentum)
+        self.layers = nn.ModuleList()
+        self.latent_channels = []
+        for i in range(self.n_encoders):
+            self.layers.append(
+                ResEncoderBlock(
+                    in_channels, out_channels, kernel_size, n_blocks, momentum=momentum
+                )
+            )
+            self.latent_channels.append([out_channels, in_size])
+            in_channels = out_channels
+            out_channels *= 2
+            in_size //= 2
+        self.out_size = in_size
+        self.out_channel = out_channels
+
+    def forward(self, x: torch.Tensor):
+        concat_tensors: List[torch.Tensor] = []
+        x = self.bn(x)
+        for i, layer in enumerate(self.layers):
+            t, x = layer(x)
+            concat_tensors.append(t)
+        return x, concat_tensors
+
+
+class ResEncoderBlock(nn.Module):
+    def __init__(
+        self, in_channels, out_channels, kernel_size, n_blocks=1, momentum=0.01
+    ):
+        super(ResEncoderBlock, self).__init__()
+        self.n_blocks = n_blocks
+        self.conv = nn.ModuleList()
+        self.conv.append(ConvBlockRes(in_channels, out_channels, momentum))
+        for i in range(n_blocks - 1):
+            self.conv.append(ConvBlockRes(out_channels, out_channels, momentum))
+        self.kernel_size = kernel_size
+        if self.kernel_size is not None:
+            self.pool = nn.AvgPool2d(kernel_size=kernel_size)
+
+    def forward(self, x):
+        for i, conv in enumerate(self.conv):
+            x = conv(x)
+        if self.kernel_size is not None:
+            return x, self.pool(x)
+        else:
+            return x
+
+
+class Intermediate(nn.Module):  #
+    def __init__(self, in_channels, out_channels, n_inters, n_blocks, momentum=0.01):
+        super(Intermediate, self).__init__()
+        self.n_inters = n_inters
+        self.layers = nn.ModuleList()
+        self.layers.append(
+            ResEncoderBlock(in_channels, out_channels, None, n_blocks, momentum)
+        )
+        for i in range(self.n_inters - 1):
+            self.layers.append(
+                ResEncoderBlock(out_channels, out_channels, None, n_blocks, momentum)
+            )
+
+    def forward(self, x):
+        for i, layer in enumerate(self.layers):
+            x = layer(x)
+        return x
+
+
+class ResDecoderBlock(nn.Module):
+    def __init__(self, in_channels, out_channels, stride, n_blocks=1, momentum=0.01):
+        super(ResDecoderBlock, self).__init__()
+        out_padding = (0, 1) if stride == (1, 2) else (1, 1)
+        self.n_blocks = n_blocks
+        self.conv1 = nn.Sequential(
+            nn.ConvTranspose2d(
+                in_channels=in_channels,
+                out_channels=out_channels,
+                kernel_size=(3, 3),
+                stride=stride,
+                padding=(1, 1),
+                output_padding=out_padding,
+                bias=False,
+            ),
+            nn.BatchNorm2d(out_channels, momentum=momentum),
+            nn.ReLU(),
+        )
+        self.conv2 = nn.ModuleList()
+        self.conv2.append(ConvBlockRes(out_channels * 2, out_channels, momentum))
+        for i in range(n_blocks - 1):
+            self.conv2.append(ConvBlockRes(out_channels, out_channels, momentum))
+
+    def forward(self, x, concat_tensor):
+        x = self.conv1(x)
+        x = torch.cat((x, concat_tensor), dim=1)
+        for i, conv2 in enumerate(self.conv2):
+            x = conv2(x)
+        return x
+
+
+class Decoder(nn.Module):
+    def __init__(self, in_channels, n_decoders, stride, n_blocks, momentum=0.01):
+        super(Decoder, self).__init__()
+        self.layers = nn.ModuleList()
+        self.n_decoders = n_decoders
+        for i in range(self.n_decoders):
+            out_channels = in_channels // 2
+            self.layers.append(
+                ResDecoderBlock(in_channels, out_channels, stride, n_blocks, momentum)
+            )
+            in_channels = out_channels
+
+    def forward(self, x: torch.Tensor, concat_tensors: List[torch.Tensor]):
+        for i, layer in enumerate(self.layers):
+            x = layer(x, concat_tensors[-1 - i])
+        return x
+
+
+class DeepUnet(nn.Module):
+    def __init__(
+        self,
+        kernel_size,
+        n_blocks,
+        en_de_layers=5,
+        inter_layers=4,
+        in_channels=1,
+        en_out_channels=16,
+    ):
+        super(DeepUnet, self).__init__()
+        self.encoder = Encoder(
+            in_channels, 128, en_de_layers, kernel_size, n_blocks, en_out_channels
+        )
+        self.intermediate = Intermediate(
+            self.encoder.out_channel // 2,
+            self.encoder.out_channel,
+            inter_layers,
+            n_blocks,
+        )
+        self.decoder = Decoder(
+            self.encoder.out_channel, en_de_layers, kernel_size, n_blocks
+        )
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        x, concat_tensors = self.encoder(x)
+        x = self.intermediate(x)
+        x = self.decoder(x, concat_tensors)
+        return x
+
+
+class E2E(nn.Module):
+    def __init__(
+        self,
+        n_blocks,
+        n_gru,
+        kernel_size,
+        en_de_layers=5,
+        inter_layers=4,
+        in_channels=1,
+        en_out_channels=16,
+    ):
+        super(E2E, self).__init__()
+        self.unet = DeepUnet(
+            kernel_size,
+            n_blocks,
+            en_de_layers,
+            inter_layers,
+            in_channels,
+            en_out_channels,
+        )
+        self.cnn = nn.Conv2d(en_out_channels, 3, (3, 3), padding=(1, 1))
+        if n_gru:
+            self.fc = nn.Sequential(
+                BiGRU(3 * 128, 256, n_gru),
+                nn.Linear(512, 360),
+                nn.Dropout(0.25),
+                nn.Sigmoid(),
+            )
+        else:
+            self.fc = nn.Sequential(
+                nn.Linear(3 * nn.N_MELS, nn.N_CLASS), nn.Dropout(0.25), nn.Sigmoid()
+            )
+
+    def forward(self, mel):
+        # print(mel.shape)
+        mel = mel.transpose(-1, -2).unsqueeze(1)
+        x = self.cnn(self.unet(mel)).transpose(1, 2).flatten(-2)
+        x = self.fc(x)
+        # print(x.shape)
+        return x
+
+
+class MelSpectrogram(torch.nn.Module):
+    def __init__(
+        self,
+        is_half,
+        n_mel_channels,
+        sampling_rate,
+        win_length,
+        hop_length,
+        n_fft=None,
+        mel_fmin=0,
+        mel_fmax=None,
+        clamp=1e-5,
+    ):
+        super().__init__()
+        n_fft = win_length if n_fft is None else n_fft
+        self.hann_window = {}
+        mel_basis = mel(
+            sr=sampling_rate,
+            n_fft=n_fft,
+            n_mels=n_mel_channels,
+            fmin=mel_fmin,
+            fmax=mel_fmax,
+            htk=True,
+        )
+        mel_basis = torch.from_numpy(mel_basis).float()
+        self.register_buffer("mel_basis", mel_basis)
+        self.n_fft = win_length if n_fft is None else n_fft
+        self.hop_length = hop_length
+        self.win_length = win_length
+        self.sampling_rate = sampling_rate
+        self.n_mel_channels = n_mel_channels
+        self.clamp = clamp
+        self.is_half = is_half
+
+    def forward(self, audio, keyshift=0, speed=1, center=True):
+        factor = 2 ** (keyshift / 12)
+        n_fft_new = int(np.round(self.n_fft * factor))
+        win_length_new = int(np.round(self.win_length * factor))
+        hop_length_new = int(np.round(self.hop_length * speed))
+        keyshift_key = str(keyshift) + "_" + str(audio.device)
+        if keyshift_key not in self.hann_window:
+            self.hann_window[keyshift_key] = torch.hann_window(win_length_new).to(
+                audio.device
+            )
+        if "privateuseone" in str(audio.device):
+            if not hasattr(self, "stft"):
+                self.stft = STFT(
+                    filter_length=n_fft_new,
+                    hop_length=hop_length_new,
+                    win_length=win_length_new,
+                    window="hann",
+                ).to(audio.device)
+            magnitude = self.stft.transform(audio)
+        else:
+            fft = torch.stft(
+                audio,
+                n_fft=n_fft_new,
+                hop_length=hop_length_new,
+                win_length=win_length_new,
+                window=self.hann_window[keyshift_key],
+                center=center,
+                return_complex=True,
+            )
+            magnitude = torch.sqrt(fft.real.pow(2) + fft.imag.pow(2))
+        if keyshift != 0:
+            size = self.n_fft // 2 + 1
+            resize = magnitude.size(1)
+            if resize < size:
+                magnitude = F.pad(magnitude, (0, 0, 0, size - resize))
+            magnitude = magnitude[:, :size, :] * self.win_length / win_length_new
+        mel_output = torch.matmul(self.mel_basis, magnitude)
+        if self.is_half == True:
+            mel_output = mel_output.half()
+        log_mel_spec = torch.log(torch.clamp(mel_output, min=self.clamp))
+        return log_mel_spec
+
+
+class RMVPE:
+    def __init__(self, model_path: str, is_half, device=None, use_jit=False):
+        self.resample_kernel = {}
+        self.resample_kernel = {}
+        self.is_half = is_half
+        if device is None:
+            device = "cuda:0" if torch.cuda.is_available() else "cpu"
+        self.device = device
+        self.mel_extractor = MelSpectrogram(
+            is_half, 128, 16000, 1024, 160, None, 30, 8000
+        ).to(device)
+        if "privateuseone" in str(device):
+            import onnxruntime as ort
+
+            ort_session = ort.InferenceSession(
+                "%s/rmvpe.onnx" % os.environ["rmvpe_root"],
+                providers=["DmlExecutionProvider"],
+            )
+            self.model = ort_session
+        else:
+            if str(self.device) == "cuda":
+                self.device = torch.device("cuda:0")
+
+            def get_jit_model():
+                jit_model_path = model_path.rstrip(".pth")
+                jit_model_path += ".half.jit" if is_half else ".jit"
+                reload = False
+                if os.path.exists(jit_model_path):
+                    ckpt = jit.load(jit_model_path)
+                    model_device = ckpt["device"]
+                    if model_device != str(self.device):
+                        reload = True
+                else:
+                    reload = True
+
+                if reload:
+                    ckpt = jit.rmvpe_jit_export(
+                        model_path=model_path,
+                        mode="script",
+                        inputs_path=None,
+                        save_path=jit_model_path,
+                        device=device,
+                        is_half=is_half,
+                    )
+                model = torch.jit.load(BytesIO(ckpt["model"]), map_location=device)
+                return model
+
+            def get_default_model():
+                model = E2E(4, 1, (2, 2))
+                ckpt = torch.load(model_path, map_location="cpu")
+                model.load_state_dict(ckpt)
+                model.eval()
+                if is_half:
+                    model = model.half()
+                else:
+                    model = model.float()
+                return model
+
+            if use_jit:
+                if is_half and "cpu" in str(self.device):
+                    logger.warning(
+                        "Use default rmvpe model. \
+                                 Jit is not supported on the CPU for half floating point"
+                    )
+                    self.model = get_default_model()
+                else:
+                    self.model = get_jit_model()
+            else:
+                self.model = get_default_model()
+
+            self.model = self.model.to(device)
+        cents_mapping = 20 * np.arange(360) + 1997.3794084376191
+        self.cents_mapping = np.pad(cents_mapping, (4, 4))  # 368
+
+    def mel2hidden(self, mel):
+        with torch.no_grad():
+            n_frames = mel.shape[-1]
+            n_pad = 32 * ((n_frames - 1) // 32 + 1) - n_frames
+            if n_pad > 0:
+                mel = F.pad(mel, (0, n_pad), mode="constant")
+            if "privateuseone" in str(self.device):
+                onnx_input_name = self.model.get_inputs()[0].name
+                onnx_outputs_names = self.model.get_outputs()[0].name
+                hidden = self.model.run(
+                    [onnx_outputs_names],
+                    input_feed={onnx_input_name: mel.cpu().numpy()},
+                )[0]
+            else:
+                mel = mel.half() if self.is_half else mel.float()
+                hidden = self.model(mel)
+            return hidden[:, :n_frames]
+
+    def decode(self, hidden, thred=0.03):
+        cents_pred = self.to_local_average_cents(hidden, thred=thred)
+        f0 = 10 * (2 ** (cents_pred / 1200))
+        f0[f0 == 10] = 0
+        # f0 = np.array([10 * (2 ** (cent_pred / 1200)) if cent_pred else 0 for cent_pred in cents_pred])
+        return f0
+
+    def infer_from_audio(self, audio, thred=0.03):
+        # torch.cuda.synchronize()
+        t0 = ttime()
+        mel = self.mel_extractor(
+            torch.from_numpy(audio).float().to(self.device).unsqueeze(0), center=True
+        )
+        # print(123123123,mel.device.type)
+        # torch.cuda.synchronize()
+        t1 = ttime()
+        hidden = self.mel2hidden(mel)
+        # torch.cuda.synchronize()
+        t2 = ttime()
+        # print(234234,hidden.device.type)
+        if "privateuseone" not in str(self.device):
+            hidden = hidden.squeeze(0).cpu().numpy()
+        else:
+            hidden = hidden[0]
+        if self.is_half == True:
+            hidden = hidden.astype("float32")
+
+        f0 = self.decode(hidden, thred=thred)
+        # torch.cuda.synchronize()
+        t3 = ttime()
+        # print("hmvpe:%s\t%s\t%s\t%s"%(t1-t0,t2-t1,t3-t2,t3-t0))
+        return f0
+
+    def to_local_average_cents(self, salience, thred=0.05):
+        # t0 = ttime()
+        center = np.argmax(salience, axis=1)  # 帧长#index
+        salience = np.pad(salience, ((0, 0), (4, 4)))  # 帧长,368
+        # t1 = ttime()
+        center += 4
+        todo_salience = []
+        todo_cents_mapping = []
+        starts = center - 4
+        ends = center + 5
+        for idx in range(salience.shape[0]):
+            todo_salience.append(salience[:, starts[idx] : ends[idx]][idx])
+            todo_cents_mapping.append(self.cents_mapping[starts[idx] : ends[idx]])
+        # t2 = ttime()
+        todo_salience = np.array(todo_salience)  # 帧长，9
+        todo_cents_mapping = np.array(todo_cents_mapping)  # 帧长，9
+        product_sum = np.sum(todo_salience * todo_cents_mapping, 1)
+        weight_sum = np.sum(todo_salience, 1)  # 帧长
+        devided = product_sum / weight_sum  # 帧长
+        # t3 = ttime()
+        maxx = np.max(salience, axis=1)  # 帧长
+        devided[maxx <= thred] = 0
+        # t4 = ttime()
+        # print("decode:%s\t%s\t%s\t%s" % (t1 - t0, t2 - t1, t3 - t2, t4 - t3))
+        return devided
+
+
+if __name__ == "__main__":
+    import librosa
+    import soundfile as sf
+
+    audio, sampling_rate = sf.read(r"C:\Users\liujing04\Desktop\Z\冬之花clip1.wav")
+    if len(audio.shape) > 1:
+        audio = librosa.to_mono(audio.transpose(1, 0))
+    audio_bak = audio.copy()
+    if sampling_rate != 16000:
+        audio = librosa.resample(audio, orig_sr=sampling_rate, target_sr=16000)
+    model_path = r"D:\BaiduNetdiskDownload\RVC-beta-v2-0727AMD_realtime\rmvpe.pt"
+    thred = 0.03  # 0.01
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    rmvpe = RMVPE(model_path, is_half=False, device=device)
+    t0 = ttime()
+    f0 = rmvpe.infer_from_audio(audio, thred=thred)
+    # f0 = rmvpe.infer_from_audio(audio, thred=thred)
+    # f0 = rmvpe.infer_from_audio(audio, thred=thred)
+    # f0 = rmvpe.infer_from_audio(audio, thred=thred)
+    # f0 = rmvpe.infer_from_audio(audio, thred=thred)
+    t1 = ttime()
+    logger.info("%s %.2f", f0.shape, t1 - t0)
diff --git a/rvc/lib/slicer2.py b/rvc/lib/slicer2.py
new file mode 100644
index 0000000000000000000000000000000000000000..7d9d16db55e30c5c732f7fd32a234af026097e13
--- /dev/null
+++ b/rvc/lib/slicer2.py
@@ -0,0 +1,260 @@
+import numpy as np
+
+
+# This function is obtained from librosa.
+def get_rms(
+    y,
+    frame_length=2048,
+    hop_length=512,
+    pad_mode="constant",
+):
+    padding = (int(frame_length // 2), int(frame_length // 2))
+    y = np.pad(y, padding, mode=pad_mode)
+
+    axis = -1
+    # put our new within-frame axis at the end for now
+    out_strides = y.strides + tuple([y.strides[axis]])
+    # Reduce the shape on the framing axis
+    x_shape_trimmed = list(y.shape)
+    x_shape_trimmed[axis] -= frame_length - 1
+    out_shape = tuple(x_shape_trimmed) + tuple([frame_length])
+    xw = np.lib.stride_tricks.as_strided(y, shape=out_shape, strides=out_strides)
+    if axis < 0:
+        target_axis = axis - 1
+    else:
+        target_axis = axis + 1
+    xw = np.moveaxis(xw, -1, target_axis)
+    # Downsample along the target axis
+    slices = [slice(None)] * xw.ndim
+    slices[axis] = slice(0, None, hop_length)
+    x = xw[tuple(slices)]
+
+    # Calculate power
+    power = np.mean(np.abs(x) ** 2, axis=-2, keepdims=True)
+
+    return np.sqrt(power)
+
+
+class Slicer:
+    def __init__(
+        self,
+        sr: int,
+        threshold: float = -40.0,
+        min_length: int = 5000,
+        min_interval: int = 300,
+        hop_size: int = 20,
+        max_sil_kept: int = 5000,
+    ):
+        if not min_length >= min_interval >= hop_size:
+            raise ValueError(
+                "The following condition must be satisfied: min_length >= min_interval >= hop_size"
+            )
+        if not max_sil_kept >= hop_size:
+            raise ValueError(
+                "The following condition must be satisfied: max_sil_kept >= hop_size"
+            )
+        min_interval = sr * min_interval / 1000
+        self.threshold = 10 ** (threshold / 20.0)
+        self.hop_size = round(sr * hop_size / 1000)
+        self.win_size = min(round(min_interval), 4 * self.hop_size)
+        self.min_length = round(sr * min_length / 1000 / self.hop_size)
+        self.min_interval = round(min_interval / self.hop_size)
+        self.max_sil_kept = round(sr * max_sil_kept / 1000 / self.hop_size)
+
+    def _apply_slice(self, waveform, begin, end):
+        if len(waveform.shape) > 1:
+            return waveform[
+                :, begin * self.hop_size : min(waveform.shape[1], end * self.hop_size)
+            ]
+        else:
+            return waveform[
+                begin * self.hop_size : min(waveform.shape[0], end * self.hop_size)
+            ]
+
+    # @timeit
+    def slice(self, waveform):
+        if len(waveform.shape) > 1:
+            samples = waveform.mean(axis=0)
+        else:
+            samples = waveform
+        if samples.shape[0] <= self.min_length:
+            return [waveform]
+        rms_list = get_rms(
+            y=samples, frame_length=self.win_size, hop_length=self.hop_size
+        ).squeeze(0)
+        sil_tags = []
+        silence_start = None
+        clip_start = 0
+        for i, rms in enumerate(rms_list):
+            # Keep looping while frame is silent.
+            if rms < self.threshold:
+                # Record start of silent frames.
+                if silence_start is None:
+                    silence_start = i
+                continue
+            # Keep looping while frame is not silent and silence start has not been recorded.
+            if silence_start is None:
+                continue
+            # Clear recorded silence start if interval is not enough or clip is too short
+            is_leading_silence = silence_start == 0 and i > self.max_sil_kept
+            need_slice_middle = (
+                i - silence_start >= self.min_interval
+                and i - clip_start >= self.min_length
+            )
+            if not is_leading_silence and not need_slice_middle:
+                silence_start = None
+                continue
+            # Need slicing. Record the range of silent frames to be removed.
+            if i - silence_start <= self.max_sil_kept:
+                pos = rms_list[silence_start : i + 1].argmin() + silence_start
+                if silence_start == 0:
+                    sil_tags.append((0, pos))
+                else:
+                    sil_tags.append((pos, pos))
+                clip_start = pos
+            elif i - silence_start <= self.max_sil_kept * 2:
+                pos = rms_list[
+                    i - self.max_sil_kept : silence_start + self.max_sil_kept + 1
+                ].argmin()
+                pos += i - self.max_sil_kept
+                pos_l = (
+                    rms_list[
+                        silence_start : silence_start + self.max_sil_kept + 1
+                    ].argmin()
+                    + silence_start
+                )
+                pos_r = (
+                    rms_list[i - self.max_sil_kept : i + 1].argmin()
+                    + i
+                    - self.max_sil_kept
+                )
+                if silence_start == 0:
+                    sil_tags.append((0, pos_r))
+                    clip_start = pos_r
+                else:
+                    sil_tags.append((min(pos_l, pos), max(pos_r, pos)))
+                    clip_start = max(pos_r, pos)
+            else:
+                pos_l = (
+                    rms_list[
+                        silence_start : silence_start + self.max_sil_kept + 1
+                    ].argmin()
+                    + silence_start
+                )
+                pos_r = (
+                    rms_list[i - self.max_sil_kept : i + 1].argmin()
+                    + i
+                    - self.max_sil_kept
+                )
+                if silence_start == 0:
+                    sil_tags.append((0, pos_r))
+                else:
+                    sil_tags.append((pos_l, pos_r))
+                clip_start = pos_r
+            silence_start = None
+        # Deal with trailing silence.
+        total_frames = rms_list.shape[0]
+        if (
+            silence_start is not None
+            and total_frames - silence_start >= self.min_interval
+        ):
+            silence_end = min(total_frames, silence_start + self.max_sil_kept)
+            pos = rms_list[silence_start : silence_end + 1].argmin() + silence_start
+            sil_tags.append((pos, total_frames + 1))
+        # Apply and return slices.
+        if len(sil_tags) == 0:
+            return [waveform]
+        else:
+            chunks = []
+            if sil_tags[0][0] > 0:
+                chunks.append(self._apply_slice(waveform, 0, sil_tags[0][0]))
+            for i in range(len(sil_tags) - 1):
+                chunks.append(
+                    self._apply_slice(waveform, sil_tags[i][1], sil_tags[i + 1][0])
+                )
+            if sil_tags[-1][1] < total_frames:
+                chunks.append(
+                    self._apply_slice(waveform, sil_tags[-1][1], total_frames)
+                )
+            return chunks
+
+
+def main():
+    import os.path
+    from argparse import ArgumentParser
+
+    import librosa
+    import soundfile
+
+    parser = ArgumentParser()
+    parser.add_argument("audio", type=str, help="The audio to be sliced")
+    parser.add_argument(
+        "--out", type=str, help="Output directory of the sliced audio clips"
+    )
+    parser.add_argument(
+        "--db_thresh",
+        type=float,
+        required=False,
+        default=-40,
+        help="The dB threshold for silence detection",
+    )
+    parser.add_argument(
+        "--min_length",
+        type=int,
+        required=False,
+        default=5000,
+        help="The minimum milliseconds required for each sliced audio clip",
+    )
+    parser.add_argument(
+        "--min_interval",
+        type=int,
+        required=False,
+        default=300,
+        help="The minimum milliseconds for a silence part to be sliced",
+    )
+    parser.add_argument(
+        "--hop_size",
+        type=int,
+        required=False,
+        default=10,
+        help="Frame length in milliseconds",
+    )
+    parser.add_argument(
+        "--max_sil_kept",
+        type=int,
+        required=False,
+        default=500,
+        help="The maximum silence length kept around the sliced clip, presented in milliseconds",
+    )
+    args = parser.parse_args()
+    out = args.out
+    if out is None:
+        out = os.path.dirname(os.path.abspath(args.audio))
+    audio, sr = librosa.load(args.audio, sr=None, mono=False)
+    slicer = Slicer(
+        sr=sr,
+        threshold=args.db_thresh,
+        min_length=args.min_length,
+        min_interval=args.min_interval,
+        hop_size=args.hop_size,
+        max_sil_kept=args.max_sil_kept,
+    )
+    chunks = slicer.slice(audio)
+    if not os.path.exists(out):
+        os.makedirs(out)
+    for i, chunk in enumerate(chunks):
+        if len(chunk.shape) > 1:
+            chunk = chunk.T
+        soundfile.write(
+            os.path.join(
+                out,
+                f"%s_%d.wav"
+                % (os.path.basename(args.audio).rsplit(".", maxsplit=1)[0], i),
+            ),
+            chunk,
+            sr,
+        )
+
+
+if __name__ == "__main__":
+    main()
diff --git a/rvc/lib/train/architecture/v1.yml b/rvc/lib/train/architecture/v1.yml
new file mode 100644
index 0000000000000000000000000000000000000000..f0891bf91eb9c3cfe45126af29c79ece31e91c0c
--- /dev/null
+++ b/rvc/lib/train/architecture/v1.yml
@@ -0,0 +1,57 @@
+32k:
+    filter_length: 513,
+    a?: 32,
+    inter_channels: 192,
+    hidden_channels: 192,
+    filter_channels: 768,
+    n_heads: 2,
+    kernen_layersl_size: 6,
+    kernel_size: 3,
+    p_dropout: 0,
+    resblock: "1",
+    resblock_kernel_sizes: [3, 7, 11],
+    resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
+    upsample_rates:  [10, 4, 2, 2, 2],
+    upsample_initial_channel: 512,
+    upsample_kernel_sizes: [16, 16, 4, 4, 4],
+    spk_embed_dim: 109,
+    gin_channels: 256,
+    sampling_rate: 32000,
+40k:
+    filter_length: 1025,
+    a?: 32, # What?
+    inter_channels: 192,
+    hidden_channels: 192,
+    filter_channels: 768,
+    n_heads: 2,
+    kernen_layersl_size: 6,
+    kernel_size: 3,
+    p_dropout: 0,
+    resblock: "1",
+    resblock_kernel_sizes: [3, 7, 11],
+    resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
+    upsample_rates: [10, 10, 2, 2],
+    upsample_initial_channel: 512,
+    upsample_kernel_sizes: [16, 16, 4, 4],
+    spk_embed_dim: 109,
+    gin_channels: 256,
+    sampling_rate:  40000,
+48k:
+    filter_length: 1025,
+    a?: 32,
+    inter_channels: 192,
+    hidden_channels: 192,
+    filter_channels: 768,
+    n_heads: 2,
+    kernen_layersl_size: 6,
+    kernel_size: 3,
+    p_dropout: 0,
+    resblock: "1",
+    resblock_kernel_sizes: [3, 7, 11],
+    resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
+    upsample_rates: [10, 6, 2, 2, 2],
+    upsample_initial_channel: 512,
+    upsample_kernel_sizes: [16, 16, 4, 4, 4],
+    spk_embed_dim: 109,
+    gin_channels: 256,
+    sampling_rate: 48000,
diff --git a/rvc/lib/train/architecture/v2.yml b/rvc/lib/train/architecture/v2.yml
new file mode 100644
index 0000000000000000000000000000000000000000..88534d9c5c67993c48147f2eeed489a88e21f917
--- /dev/null
+++ b/rvc/lib/train/architecture/v2.yml
@@ -0,0 +1,38 @@
+32k:
+    filter_length: 513,
+    a?: 32,
+    inter_channels: 192,
+    hidden_channels: 192,
+    filter_channels: 768,
+    n_heads: 2,
+    kernen_layersl_size: 6,
+    kernel_size: 3,
+    p_dropout: 0,
+    resblock: "1",
+    resblock_kernel_sizes: [3, 7, 11],
+    resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
+    upsample_rates:  [10, 4, 2, 2, 2],
+    upsample_initial_channel: 512,
+    upsample_kernel_sizes: [16, 16, 4, 4, 4],
+    spk_embed_dim: 109,
+    gin_channels: 256,
+    sampling_rate: 32000,
+48k:
+    filter_length: 1025,
+    a?: 32,
+    inter_channels: 192,
+    hidden_channels: 192,
+    filter_channels: 768,
+    n_heads: 2,
+    kernen_layersl_size: 6,
+    kernel_size: 3,
+    p_dropout: 0,
+    resblock: "1",
+    resblock_kernel_sizes: [3, 7, 11],
+    resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
+    upsample_rates: [12, 10, 2, 2],
+    upsample_initial_channel: 512,
+    upsample_kernel_sizes: [24, 20, 4, 4],
+    spk_embed_dim: 109,
+    gin_channels: 256,
+    sampling_rate: 48000,
diff --git a/rvc/lib/train/data_utils.py b/rvc/lib/train/data_utils.py
new file mode 100644
index 0000000000000000000000000000000000000000..8d23c31d2e590d15a25a6997b58f9cad1277d886
--- /dev/null
+++ b/rvc/lib/train/data_utils.py
@@ -0,0 +1,517 @@
+import logging
+import os
+import traceback
+
+logger = logging.getLogger(__name__)
+
+import numpy as np
+import torch
+import torch.utils.data
+
+from rvc.lib.train.mel_processing import spectrogram_torch
+from rvc.lib.train.utils import load_filepaths_and_text, load_wav_to_torch
+
+
+class TextAudioLoaderMultiNSFsid(torch.utils.data.Dataset):
+    """
+    1) loads audio, text pairs
+    2) normalizes text and converts them to sequences of integers
+    3) computes spectrograms from audio files.
+    """
+
+    def __init__(self, audiopaths_and_text, hparams):
+        self.audiopaths_and_text = load_filepaths_and_text(audiopaths_and_text)
+        self.max_wav_value = hparams.max_wav_value
+        self.sampling_rate = hparams.sampling_rate
+        self.filter_length = hparams.filter_length
+        self.hop_length = hparams.hop_length
+        self.win_length = hparams.win_length
+        self.sampling_rate = hparams.sampling_rate
+        self.min_text_len = getattr(hparams, "min_text_len", 1)
+        self.max_text_len = getattr(hparams, "max_text_len", 5000)
+        self._filter()
+
+    def _filter(self):
+        """
+        Filter text & store spec lengths
+        """
+        # Store spectrogram lengths for Bucketing
+        # wav_length ~= file_size / (wav_channels * Bytes per dim) = file_size / (1 * 2)
+        # spec_length = wav_length // hop_length
+        audiopaths_and_text_new = []
+        lengths = []
+        for audiopath, text, pitch, pitchf, dv in self.audiopaths_and_text:
+            if self.min_text_len <= len(text) and len(text) <= self.max_text_len:
+                audiopaths_and_text_new.append([audiopath, text, pitch, pitchf, dv])
+                lengths.append(os.path.getsize(audiopath) // (3 * self.hop_length))
+        self.audiopaths_and_text = audiopaths_and_text_new
+        self.lengths = lengths
+
+    def get_sid(self, sid):
+        sid = torch.LongTensor([int(sid)])
+        return sid
+
+    def get_audio_text_pair(self, audiopath_and_text):
+        # separate filename and text
+        file = audiopath_and_text[0]
+        phone = audiopath_and_text[1]
+        pitch = audiopath_and_text[2]
+        pitchf = audiopath_and_text[3]
+        dv = audiopath_and_text[4]
+
+        phone, pitch, pitchf = self.get_labels(phone, pitch, pitchf)
+        spec, wav = self.get_audio(file)
+        dv = self.get_sid(dv)
+
+        len_phone = phone.size()[0]
+        len_spec = spec.size()[-1]
+        # print(123,phone.shape,pitch.shape,spec.shape)
+        if len_phone != len_spec:
+            len_min = min(len_phone, len_spec)
+            # amor
+            len_wav = len_min * self.hop_length
+
+            spec = spec[:, :len_min]
+            wav = wav[:, :len_wav]
+
+            phone = phone[:len_min, :]
+            pitch = pitch[:len_min]
+            pitchf = pitchf[:len_min]
+
+        return (spec, wav, phone, pitch, pitchf, dv)
+
+    def get_labels(self, phone, pitch, pitchf):
+        phone = np.load(phone)
+        phone = np.repeat(phone, 2, axis=0)
+        pitch = np.load(pitch)
+        pitchf = np.load(pitchf)
+        n_num = min(phone.shape[0], 900)  # DistributedBucketSampler
+        # print(234,phone.shape,pitch.shape)
+        phone = phone[:n_num, :]
+        pitch = pitch[:n_num]
+        pitchf = pitchf[:n_num]
+        phone = torch.FloatTensor(phone)
+        pitch = torch.LongTensor(pitch)
+        pitchf = torch.FloatTensor(pitchf)
+        return phone, pitch, pitchf
+
+    def get_audio(self, filename):
+        audio, sampling_rate = load_wav_to_torch(filename)
+        if sampling_rate != self.sampling_rate:
+            raise ValueError(
+                "{} SR doesn't match target {} SR".format(
+                    sampling_rate, self.sampling_rate
+                )
+            )
+        audio_norm = audio
+        #        audio_norm = audio / self.max_wav_value
+        #        audio_norm = audio / np.abs(audio).max()
+
+        audio_norm = audio_norm.unsqueeze(0)
+        spec_filename = filename.replace(".wav", ".spec.pt")
+        if os.path.exists(spec_filename):
+            try:
+                spec = torch.load(spec_filename)
+            except:
+                logger.warning("%s %s", spec_filename, traceback.format_exc())
+                spec = spectrogram_torch(
+                    audio_norm,
+                    self.filter_length,
+                    self.sampling_rate,
+                    self.hop_length,
+                    self.win_length,
+                    center=False,
+                )
+                spec = torch.squeeze(spec, 0)
+                torch.save(spec, spec_filename, _use_new_zipfile_serialization=False)
+        else:
+            spec = spectrogram_torch(
+                audio_norm,
+                self.filter_length,
+                self.sampling_rate,
+                self.hop_length,
+                self.win_length,
+                center=False,
+            )
+            spec = torch.squeeze(spec, 0)
+            torch.save(spec, spec_filename, _use_new_zipfile_serialization=False)
+        return spec, audio_norm
+
+    def __getitem__(self, index):
+        return self.get_audio_text_pair(self.audiopaths_and_text[index])
+
+    def __len__(self):
+        return len(self.audiopaths_and_text)
+
+
+class TextAudioCollateMultiNSFsid:
+    """Zero-pads model inputs and targets"""
+
+    def __init__(self, return_ids=False):
+        self.return_ids = return_ids
+
+    def __call__(self, batch):
+        """Collate's training batch from normalized text and aduio
+        PARAMS
+        ------
+        batch: [text_normalized, spec_normalized, wav_normalized]
+        """
+        # Right zero-pad all one-hot text sequences to max input length
+        _, ids_sorted_decreasing = torch.sort(
+            torch.LongTensor([x[0].size(1) for x in batch]), dim=0, descending=True
+        )
+
+        max_spec_len = max([x[0].size(1) for x in batch])
+        max_wave_len = max([x[1].size(1) for x in batch])
+        spec_lengths = torch.LongTensor(len(batch))
+        wave_lengths = torch.LongTensor(len(batch))
+        spec_padded = torch.FloatTensor(len(batch), batch[0][0].size(0), max_spec_len)
+        wave_padded = torch.FloatTensor(len(batch), 1, max_wave_len)
+        spec_padded.zero_()
+        wave_padded.zero_()
+
+        max_phone_len = max([x[2].size(0) for x in batch])
+        phone_lengths = torch.LongTensor(len(batch))
+        phone_padded = torch.FloatTensor(
+            len(batch), max_phone_len, batch[0][2].shape[1]
+        )  # (spec, wav, phone, pitch)
+        pitch_padded = torch.LongTensor(len(batch), max_phone_len)
+        pitchf_padded = torch.FloatTensor(len(batch), max_phone_len)
+        phone_padded.zero_()
+        pitch_padded.zero_()
+        pitchf_padded.zero_()
+        # dv = torch.FloatTensor(len(batch), 256)#gin=256
+        sid = torch.LongTensor(len(batch))
+
+        for i in range(len(ids_sorted_decreasing)):
+            row = batch[ids_sorted_decreasing[i]]
+
+            spec = row[0]
+            spec_padded[i, :, : spec.size(1)] = spec
+            spec_lengths[i] = spec.size(1)
+
+            wave = row[1]
+            wave_padded[i, :, : wave.size(1)] = wave
+            wave_lengths[i] = wave.size(1)
+
+            phone = row[2]
+            phone_padded[i, : phone.size(0), :] = phone
+            phone_lengths[i] = phone.size(0)
+
+            pitch = row[3]
+            pitch_padded[i, : pitch.size(0)] = pitch
+            pitchf = row[4]
+            pitchf_padded[i, : pitchf.size(0)] = pitchf
+
+            # dv[i] = row[5]
+            sid[i] = row[5]
+
+        return (
+            phone_padded,
+            phone_lengths,
+            pitch_padded,
+            pitchf_padded,
+            spec_padded,
+            spec_lengths,
+            wave_padded,
+            wave_lengths,
+            # dv
+            sid,
+        )
+
+
+class TextAudioLoader(torch.utils.data.Dataset):
+    """
+    1) loads audio, text pairs
+    2) normalizes text and converts them to sequences of integers
+    3) computes spectrograms from audio files.
+    """
+
+    def __init__(self, audiopaths_and_text, hparams):
+        self.audiopaths_and_text = load_filepaths_and_text(audiopaths_and_text)
+        self.max_wav_value = hparams.max_wav_value
+        self.sampling_rate = hparams.sampling_rate
+        self.filter_length = hparams.filter_length
+        self.hop_length = hparams.hop_length
+        self.win_length = hparams.win_length
+        self.sampling_rate = hparams.sampling_rate
+        self.min_text_len = getattr(hparams, "min_text_len", 1)
+        self.max_text_len = getattr(hparams, "max_text_len", 5000)
+        self._filter()
+
+    def _filter(self):
+        """
+        Filter text & store spec lengths
+        """
+        # Store spectrogram lengths for Bucketing
+        # wav_length ~= file_size / (wav_channels * Bytes per dim) = file_size / (1 * 2)
+        # spec_length = wav_length // hop_length
+        audiopaths_and_text_new = []
+        lengths = []
+        for audiopath, text, dv in self.audiopaths_and_text:
+            if self.min_text_len <= len(text) and len(text) <= self.max_text_len:
+                audiopaths_and_text_new.append([audiopath, text, dv])
+                lengths.append(os.path.getsize(audiopath) // (3 * self.hop_length))
+        self.audiopaths_and_text = audiopaths_and_text_new
+        self.lengths = lengths
+
+    def get_sid(self, sid):
+        sid = torch.LongTensor([int(sid)])
+        return sid
+
+    def get_audio_text_pair(self, audiopath_and_text):
+        # separate filename and text
+        file = audiopath_and_text[0]
+        phone = audiopath_and_text[1]
+        dv = audiopath_and_text[2]
+
+        phone = self.get_labels(phone)
+        spec, wav = self.get_audio(file)
+        dv = self.get_sid(dv)
+
+        len_phone = phone.size()[0]
+        len_spec = spec.size()[-1]
+        if len_phone != len_spec:
+            len_min = min(len_phone, len_spec)
+            len_wav = len_min * self.hop_length
+            spec = spec[:, :len_min]
+            wav = wav[:, :len_wav]
+            phone = phone[:len_min, :]
+        return (spec, wav, phone, dv)
+
+    def get_labels(self, phone):
+        phone = np.load(phone)
+        phone = np.repeat(phone, 2, axis=0)
+        n_num = min(phone.shape[0], 900)  # DistributedBucketSampler
+        phone = phone[:n_num, :]
+        phone = torch.FloatTensor(phone)
+        return phone
+
+    def get_audio(self, filename):
+        audio, sampling_rate = load_wav_to_torch(filename)
+        if sampling_rate != self.sampling_rate:
+            raise ValueError(
+                "{} SR doesn't match target {} SR".format(
+                    sampling_rate, self.sampling_rate
+                )
+            )
+        audio_norm = audio
+        #        audio_norm = audio / self.max_wav_value
+        #        audio_norm = audio / np.abs(audio).max()
+
+        audio_norm = audio_norm.unsqueeze(0)
+        spec_filename = filename.replace(".wav", ".spec.pt")
+        if os.path.exists(spec_filename):
+            try:
+                spec = torch.load(spec_filename)
+            except:
+                logger.warning("%s %s", spec_filename, traceback.format_exc())
+                spec = spectrogram_torch(
+                    audio_norm,
+                    self.filter_length,
+                    self.sampling_rate,
+                    self.hop_length,
+                    self.win_length,
+                    center=False,
+                )
+                spec = torch.squeeze(spec, 0)
+                torch.save(spec, spec_filename, _use_new_zipfile_serialization=False)
+        else:
+            spec = spectrogram_torch(
+                audio_norm,
+                self.filter_length,
+                self.sampling_rate,
+                self.hop_length,
+                self.win_length,
+                center=False,
+            )
+            spec = torch.squeeze(spec, 0)
+            torch.save(spec, spec_filename, _use_new_zipfile_serialization=False)
+        return spec, audio_norm
+
+    def __getitem__(self, index):
+        return self.get_audio_text_pair(self.audiopaths_and_text[index])
+
+    def __len__(self):
+        return len(self.audiopaths_and_text)
+
+
+class TextAudioCollate:
+    """Zero-pads model inputs and targets"""
+
+    def __init__(self, return_ids=False):
+        self.return_ids = return_ids
+
+    def __call__(self, batch):
+        """Collate's training batch from normalized text and aduio
+        PARAMS
+        ------
+        batch: [text_normalized, spec_normalized, wav_normalized]
+        """
+        # Right zero-pad all one-hot text sequences to max input length
+        _, ids_sorted_decreasing = torch.sort(
+            torch.LongTensor([x[0].size(1) for x in batch]), dim=0, descending=True
+        )
+
+        max_spec_len = max([x[0].size(1) for x in batch])
+        max_wave_len = max([x[1].size(1) for x in batch])
+        spec_lengths = torch.LongTensor(len(batch))
+        wave_lengths = torch.LongTensor(len(batch))
+        spec_padded = torch.FloatTensor(len(batch), batch[0][0].size(0), max_spec_len)
+        wave_padded = torch.FloatTensor(len(batch), 1, max_wave_len)
+        spec_padded.zero_()
+        wave_padded.zero_()
+
+        max_phone_len = max([x[2].size(0) for x in batch])
+        phone_lengths = torch.LongTensor(len(batch))
+        phone_padded = torch.FloatTensor(
+            len(batch), max_phone_len, batch[0][2].shape[1]
+        )
+        phone_padded.zero_()
+        sid = torch.LongTensor(len(batch))
+
+        for i in range(len(ids_sorted_decreasing)):
+            row = batch[ids_sorted_decreasing[i]]
+
+            spec = row[0]
+            spec_padded[i, :, : spec.size(1)] = spec
+            spec_lengths[i] = spec.size(1)
+
+            wave = row[1]
+            wave_padded[i, :, : wave.size(1)] = wave
+            wave_lengths[i] = wave.size(1)
+
+            phone = row[2]
+            phone_padded[i, : phone.size(0), :] = phone
+            phone_lengths[i] = phone.size(0)
+
+            sid[i] = row[3]
+
+        return (
+            phone_padded,
+            phone_lengths,
+            spec_padded,
+            spec_lengths,
+            wave_padded,
+            wave_lengths,
+            sid,
+        )
+
+
+class DistributedBucketSampler(torch.utils.data.distributed.DistributedSampler):
+    """
+    Maintain similar input lengths in a batch.
+    Length groups are specified by boundaries.
+    Ex) boundaries = [b1, b2, b3] -> any batch is included either {x | b1 < length(x) <=b2} or {x | b2 < length(x) <= b3}.
+
+    It removes samples which are not included in the boundaries.
+    Ex) boundaries = [b1, b2, b3] -> any x s.t. length(x) <= b1 or length(x) > b3 are discarded.
+    """
+
+    def __init__(
+        self,
+        dataset,
+        batch_size,
+        boundaries,
+        num_replicas=None,
+        rank=None,
+        shuffle=True,
+    ):
+        super().__init__(dataset, num_replicas=num_replicas, rank=rank, shuffle=shuffle)
+        self.lengths = dataset.lengths
+        self.batch_size = batch_size
+        self.boundaries = boundaries
+
+        self.buckets, self.num_samples_per_bucket = self._create_buckets()
+        self.total_size = sum(self.num_samples_per_bucket)
+        self.num_samples = self.total_size // self.num_replicas
+
+    def _create_buckets(self):
+        buckets = [[] for _ in range(len(self.boundaries) - 1)]
+        for i in range(len(self.lengths)):
+            length = self.lengths[i]
+            idx_bucket = self._bisect(length)
+            if idx_bucket != -1:
+                buckets[idx_bucket].append(i)
+
+        for i in range(len(buckets) - 1, -1, -1):  #
+            if len(buckets[i]) == 0:
+                buckets.pop(i)
+                self.boundaries.pop(i + 1)
+
+        num_samples_per_bucket = []
+        for i in range(len(buckets)):
+            len_bucket = len(buckets[i])
+            total_batch_size = self.num_replicas * self.batch_size
+            rem = (
+                total_batch_size - (len_bucket % total_batch_size)
+            ) % total_batch_size
+            num_samples_per_bucket.append(len_bucket + rem)
+        return buckets, num_samples_per_bucket
+
+    def __iter__(self):
+        # deterministically shuffle based on epoch
+        g = torch.Generator()
+        g.manual_seed(self.epoch)
+
+        indices = []
+        if self.shuffle:
+            for bucket in self.buckets:
+                indices.append(torch.randperm(len(bucket), generator=g).tolist())
+        else:
+            for bucket in self.buckets:
+                indices.append(list(range(len(bucket))))
+
+        batches = []
+        for i in range(len(self.buckets)):
+            bucket = self.buckets[i]
+            len_bucket = len(bucket)
+            ids_bucket = indices[i]
+            num_samples_bucket = self.num_samples_per_bucket[i]
+
+            # add extra samples to make it evenly divisible
+            rem = num_samples_bucket - len_bucket
+            ids_bucket = (
+                ids_bucket
+                + ids_bucket * (rem // len_bucket)
+                + ids_bucket[: (rem % len_bucket)]
+            )
+
+            # subsample
+            ids_bucket = ids_bucket[self.rank :: self.num_replicas]
+
+            # batching
+            for j in range(len(ids_bucket) // self.batch_size):
+                batch = [
+                    bucket[idx]
+                    for idx in ids_bucket[
+                        j * self.batch_size : (j + 1) * self.batch_size
+                    ]
+                ]
+                batches.append(batch)
+
+        if self.shuffle:
+            batch_ids = torch.randperm(len(batches), generator=g).tolist()
+            batches = [batches[i] for i in batch_ids]
+        self.batches = batches
+
+        assert len(self.batches) * self.batch_size == self.num_samples
+        return iter(self.batches)
+
+    def _bisect(self, x, lo=0, hi=None):
+        if hi is None:
+            hi = len(self.boundaries) - 1
+
+        if hi > lo:
+            mid = (hi + lo) // 2
+            if self.boundaries[mid] < x and x <= self.boundaries[mid + 1]:
+                return mid
+            elif x <= self.boundaries[mid]:
+                return self._bisect(x, lo, mid)
+            else:
+                return self._bisect(x, mid + 1, hi)
+        else:
+            return -1
+
+    def __len__(self):
+        return self.num_samples // self.batch_size
diff --git a/rvc/lib/train/losses.py b/rvc/lib/train/losses.py
new file mode 100644
index 0000000000000000000000000000000000000000..aa7bd81cf596884a8b33e802ae49254d7810a860
--- /dev/null
+++ b/rvc/lib/train/losses.py
@@ -0,0 +1,58 @@
+import torch
+
+
+def feature_loss(fmap_r, fmap_g):
+    loss = 0
+    for dr, dg in zip(fmap_r, fmap_g):
+        for rl, gl in zip(dr, dg):
+            rl = rl.float().detach()
+            gl = gl.float()
+            loss += torch.mean(torch.abs(rl - gl))
+
+    return loss * 2
+
+
+def discriminator_loss(disc_real_outputs, disc_generated_outputs):
+    loss = 0
+    r_losses = []
+    g_losses = []
+    for dr, dg in zip(disc_real_outputs, disc_generated_outputs):
+        dr = dr.float()
+        dg = dg.float()
+        r_loss = torch.mean((1 - dr) ** 2)
+        g_loss = torch.mean(dg**2)
+        loss += r_loss + g_loss
+        r_losses.append(r_loss.item())
+        g_losses.append(g_loss.item())
+
+    return loss, r_losses, g_losses
+
+
+def generator_loss(disc_outputs):
+    loss = 0
+    gen_losses = []
+    for dg in disc_outputs:
+        dg = dg.float()
+        l = torch.mean((1 - dg) ** 2)
+        gen_losses.append(l)
+        loss += l
+
+    return loss, gen_losses
+
+
+def kl_loss(z_p, logs_q, m_p, logs_p, z_mask):
+    """
+    z_p, logs_q: [b, h, t_t]
+    m_p, logs_p: [b, h, t_t]
+    """
+    z_p = z_p.float()
+    logs_q = logs_q.float()
+    m_p = m_p.float()
+    logs_p = logs_p.float()
+    z_mask = z_mask.float()
+
+    kl = logs_p - logs_q - 0.5
+    kl += 0.5 * ((z_p - m_p) ** 2) * torch.exp(-2.0 * logs_p)
+    kl = torch.sum(kl * z_mask)
+    l = kl / torch.sum(z_mask)
+    return l
diff --git a/rvc/lib/train/mel_processing.py b/rvc/lib/train/mel_processing.py
new file mode 100644
index 0000000000000000000000000000000000000000..3be443f2cff9a124595c144041081e23270a5f43
--- /dev/null
+++ b/rvc/lib/train/mel_processing.py
@@ -0,0 +1,133 @@
+import logging
+
+import torch
+import torch.utils.data
+from librosa.filters import mel as librosa_mel_fn
+
+logger = logging.getLogger(__name__)
+
+MAX_WAV_VALUE = 32768.0
+
+
+def dynamic_range_compression_torch(x, C=1, clip_val=1e-5):
+    """
+    PARAMS
+    ------
+    C: compression factor
+    """
+    return torch.log(torch.clamp(x, min=clip_val) * C)
+
+
+def dynamic_range_decompression_torch(x, C=1):
+    """
+    PARAMS
+    ------
+    C: compression factor used to compress
+    """
+    return torch.exp(x) / C
+
+
+def spectral_normalize_torch(magnitudes):
+    return dynamic_range_compression_torch(magnitudes)
+
+
+def spectral_de_normalize_torch(magnitudes):
+    return dynamic_range_decompression_torch(magnitudes)
+
+
+# Reusable banks
+mel_basis = {}
+hann_window = {}
+
+
+def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False):
+    """Convert waveform into Linear-frequency Linear-amplitude spectrogram.
+
+    Args:
+        y             :: (B, T) - Audio waveforms
+        n_fft
+        sampling_rate
+        hop_size
+        win_size
+        center
+    Returns:
+        :: (B, Freq, Frame) - Linear-frequency Linear-amplitude spectrogram
+    """
+    # Validation
+    if torch.min(y) < -1.07:
+        logger.debug("min value is %s", str(torch.min(y)))
+    if torch.max(y) > 1.07:
+        logger.debug("max value is %s", str(torch.max(y)))
+
+    # Window - Cache if needed
+    global hann_window
+    dtype_device = str(y.dtype) + "_" + str(y.device)
+    wnsize_dtype_device = str(win_size) + "_" + dtype_device
+    if wnsize_dtype_device not in hann_window:
+        hann_window[wnsize_dtype_device] = torch.hann_window(win_size).to(
+            dtype=y.dtype, device=y.device
+        )
+
+    # Padding
+    y = torch.nn.functional.pad(
+        y.unsqueeze(1),
+        (int((n_fft - hop_size) / 2), int((n_fft - hop_size) / 2)),
+        mode="reflect",
+    )
+    y = y.squeeze(1)
+
+    # Complex Spectrogram :: (B, T) -> (B, Freq, Frame, RealComplex=2)
+    spec = torch.stft(
+        y,
+        n_fft,
+        hop_length=hop_size,
+        win_length=win_size,
+        window=hann_window[wnsize_dtype_device],
+        center=center,
+        pad_mode="reflect",
+        normalized=False,
+        onesided=True,
+        return_complex=False,
+    )
+
+    # Linear-frequency Linear-amplitude spectrogram :: (B, Freq, Frame, RealComplex=2) -> (B, Freq, Frame)
+    spec = torch.sqrt(spec.pow(2).sum(-1) + 1e-6)
+    return spec
+
+
+def spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax):
+    # MelBasis - Cache if needed
+    global mel_basis
+    dtype_device = str(spec.dtype) + "_" + str(spec.device)
+    fmax_dtype_device = str(fmax) + "_" + dtype_device
+    if fmax_dtype_device not in mel_basis:
+        mel = librosa_mel_fn(
+            sr=sampling_rate, n_fft=n_fft, n_mels=num_mels, fmin=fmin, fmax=fmax
+        )
+        mel_basis[fmax_dtype_device] = torch.from_numpy(mel).to(
+            dtype=spec.dtype, device=spec.device
+        )
+
+    # Mel-frequency Log-amplitude spectrogram :: (B, Freq=num_mels, Frame)
+    melspec = torch.matmul(mel_basis[fmax_dtype_device], spec)
+    melspec = spectral_normalize_torch(melspec)
+    return melspec
+
+
+def mel_spectrogram_torch(
+    y, n_fft, num_mels, sampling_rate, hop_size, win_size, fmin, fmax, center=False
+):
+    """Convert waveform into Mel-frequency Log-amplitude spectrogram.
+
+    Args:
+        y       :: (B, T)           - Waveforms
+    Returns:
+        melspec :: (B, Freq, Frame) - Mel-frequency Log-amplitude spectrogram
+    """
+    # Linear-frequency Linear-amplitude spectrogram :: (B, T) -> (B, Freq, Frame)
+    spec = spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center)
+
+    # Mel-frequency Log-amplitude spectrogram :: (B, Freq, Frame) -> (B, Freq=num_mels, Frame)
+    melspec = spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax)
+
+    return melspec
diff --git a/rvc/lib/train/process_ckpt.py b/rvc/lib/train/process_ckpt.py
new file mode 100644
index 0000000000000000000000000000000000000000..2a0515478819c496ae77a06277d4a24cb9c60734
--- /dev/null
+++ b/rvc/lib/train/process_ckpt.py
@@ -0,0 +1,260 @@
+import os
+import sys
+import traceback
+from collections import OrderedDict
+
+import torch
+from i18n.i18n import I18nAuto
+
+i18n = I18nAuto()
+
+
+def savee(ckpt, sr, if_f0, name, epoch, version, hps):
+    try:
+        opt = OrderedDict()
+        opt["weight"] = {}
+        for key in ckpt.keys():
+            if "enc_q" in key:
+                continue
+            opt["weight"][key] = ckpt[key].half()
+        opt["config"] = [
+            hps.data.filter_length // 2 + 1,
+            32,
+            hps.model.inter_channels,
+            hps.model.hidden_channels,
+            hps.model.filter_channels,
+            hps.model.n_heads,
+            hps.model.n_layers,
+            hps.model.kernel_size,
+            hps.model.p_dropout,
+            hps.model.resblock,
+            hps.model.resblock_kernel_sizes,
+            hps.model.resblock_dilation_sizes,
+            hps.model.upsample_rates,
+            hps.model.upsample_initial_channel,
+            hps.model.upsample_kernel_sizes,
+            hps.model.spk_embed_dim,
+            hps.model.gin_channels,
+            hps.data.sampling_rate,
+        ]
+        opt["info"] = "%sepoch" % epoch
+        opt["sr"] = sr
+        opt["f0"] = if_f0
+        opt["version"] = version
+        torch.save(opt, "assets/weights/%s.pth" % name)
+        return "Success."
+    except:
+        return traceback.format_exc()
+
+
+def show_info(path):
+    try:
+        a = torch.load(path, map_location="cpu")
+        return "模型信息:%s\n采样率:%s\n模型是否输入音高引导:%s\n版本:%s" % (
+            a.get("info", "None"),
+            a.get("sr", "None"),
+            a.get("f0", "None"),
+            a.get("version", "None"),
+        )
+    except:
+        return traceback.format_exc()
+
+
+def extract_small_model(path, name, sr, if_f0, info, version):
+    try:
+        ckpt = torch.load(path, map_location="cpu")
+        if "model" in ckpt:
+            ckpt = ckpt["model"]
+        opt = OrderedDict()
+        opt["weight"] = {}
+        for key in ckpt.keys():
+            if "enc_q" in key:
+                continue
+            opt["weight"][key] = ckpt[key].half()
+        if sr == "40k":
+            opt["config"] = [
+                1025,
+                32,
+                192,
+                192,
+                768,
+                2,
+                6,
+                3,
+                0,
+                "1",
+                [3, 7, 11],
+                [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
+                [10, 10, 2, 2],
+                512,
+                [16, 16, 4, 4],
+                109,
+                256,
+                40000,
+            ]
+        elif sr == "48k":
+            if version == "v1":
+                opt["config"] = [
+                    1025,
+                    32,
+                    192,
+                    192,
+                    768,
+                    2,
+                    6,
+                    3,
+                    0,
+                    "1",
+                    [3, 7, 11],
+                    [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
+                    [10, 6, 2, 2, 2],
+                    512,
+                    [16, 16, 4, 4, 4],
+                    109,
+                    256,
+                    48000,
+                ]
+            else:
+                opt["config"] = [
+                    1025,
+                    32,
+                    192,
+                    192,
+                    768,
+                    2,
+                    6,
+                    3,
+                    0,
+                    "1",
+                    [3, 7, 11],
+                    [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
+                    [12, 10, 2, 2],
+                    512,
+                    [24, 20, 4, 4],
+                    109,
+                    256,
+                    48000,
+                ]
+        elif sr == "32k":
+            if version == "v1":
+                opt["config"] = [
+                    513,
+                    32,
+                    192,
+                    192,
+                    768,
+                    2,
+                    6,
+                    3,
+                    0,
+                    "1",
+                    [3, 7, 11],
+                    [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
+                    [10, 4, 2, 2, 2],
+                    512,
+                    [16, 16, 4, 4, 4],
+                    109,
+                    256,
+                    32000,
+                ]
+            else:
+                opt["config"] = [
+                    513,
+                    32,
+                    192,
+                    192,
+                    768,
+                    2,
+                    6,
+                    3,
+                    0,
+                    "1",
+                    [3, 7, 11],
+                    [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
+                    [10, 8, 2, 2],
+                    512,
+                    [20, 16, 4, 4],
+                    109,
+                    256,
+                    32000,
+                ]
+        if info == "":
+            info = "Extracted model."
+        opt["info"] = info
+        opt["version"] = version
+        opt["sr"] = sr
+        opt["f0"] = int(if_f0)
+        torch.save(opt, "assets/weights/%s.pth" % name)
+        return "Success."
+    except:
+        return traceback.format_exc()
+
+
+def change_info(path, info, name):
+    try:
+        ckpt = torch.load(path, map_location="cpu")
+        ckpt["info"] = info
+        if name == "":
+            name = os.path.basename(path)
+        torch.save(ckpt, "assets/weights/%s" % name)
+        return "Success."
+    except:
+        return traceback.format_exc()
+
+
+def merge(path1, path2, alpha1, sr, f0, info, name, version):
+    try:
+
+        def extract(ckpt):
+            a = ckpt["model"]
+            opt = OrderedDict()
+            opt["weight"] = {}
+            for key in a.keys():
+                if "enc_q" in key:
+                    continue
+                opt["weight"][key] = a[key]
+            return opt
+
+        ckpt1 = torch.load(path1, map_location="cpu")
+        ckpt2 = torch.load(path2, map_location="cpu")
+        cfg = ckpt1["config"]
+        if "model" in ckpt1:
+            ckpt1 = extract(ckpt1)
+        else:
+            ckpt1 = ckpt1["weight"]
+        if "model" in ckpt2:
+            ckpt2 = extract(ckpt2)
+        else:
+            ckpt2 = ckpt2["weight"]
+        if sorted(list(ckpt1.keys())) != sorted(list(ckpt2.keys())):
+            return "Fail to merge the models. The model architectures are not the same."
+        opt = OrderedDict()
+        opt["weight"] = {}
+        for key in ckpt1.keys():
+            # try:
+            if key == "emb_g.weight" and ckpt1[key].shape != ckpt2[key].shape:
+                min_shape0 = min(ckpt1[key].shape[0], ckpt2[key].shape[0])
+                opt["weight"][key] = (
+                    alpha1 * (ckpt1[key][:min_shape0].float())
+                    + (1 - alpha1) * (ckpt2[key][:min_shape0].float())
+                ).half()
+            else:
+                opt["weight"][key] = (
+                    alpha1 * (ckpt1[key].float()) + (1 - alpha1) * (ckpt2[key].float())
+                ).half()
+        # except:
+        #     pdb.set_trace()
+        opt["config"] = cfg
+        """
+        if(sr=="40k"):opt["config"] = [1025, 32, 192, 192, 768, 2, 6, 3, 0, "1", [3, 7, 11], [[1, 3, 5], [1, 3, 5], [1, 3, 5]], [10, 10, 2, 2], 512, [16, 16, 4, 4,4], 109, 256, 40000]
+        elif(sr=="48k"):opt["config"] = [1025, 32, 192, 192, 768, 2, 6, 3, 0, "1", [3, 7, 11], [[1, 3, 5], [1, 3, 5], [1, 3, 5]], [10,6,2,2,2], 512, [16, 16, 4, 4], 109, 256, 48000]
+        elif(sr=="32k"):opt["config"] = [513, 32, 192, 192, 768, 2, 6, 3, 0, "1", [3, 7, 11], [[1, 3, 5], [1, 3, 5], [1, 3, 5]], [10, 4, 2, 2, 2], 512, [16, 16, 4, 4,4], 109, 256, 32000]
+        """
+        opt["sr"] = sr
+        opt["f0"] = 1 if f0 == i18n("是") else 0
+        opt["version"] = version
+        opt["info"] = info
+        torch.save(opt, "assets/weights/%s.pth" % name)
+        return "Success."
+    except:
+        return traceback.format_exc()
diff --git a/rvc/lib/train/utils.py b/rvc/lib/train/utils.py
new file mode 100644
index 0000000000000000000000000000000000000000..978509768d7057eddcecc61794df8d8a43d3f4c6
--- /dev/null
+++ b/rvc/lib/train/utils.py
@@ -0,0 +1,478 @@
+import argparse
+import glob
+import json
+import logging
+import os
+import shutil
+import subprocess
+import sys
+
+import numpy as np
+import torch
+from scipy.io.wavfile import read
+
+MATPLOTLIB_FLAG = False
+
+logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
+logger = logging
+
+
+def load_checkpoint_d(checkpoint_path, combd, sbd, optimizer=None, load_opt=1):
+    assert os.path.isfile(checkpoint_path)
+    checkpoint_dict = torch.load(checkpoint_path, map_location="cpu")
+
+    ##################
+    def go(model, bkey):
+        saved_state_dict = checkpoint_dict[bkey]
+        if hasattr(model, "module"):
+            state_dict = model.module.state_dict()
+        else:
+            state_dict = model.state_dict()
+        new_state_dict = {}
+        for k, v in state_dict.items():  # 模型需要的shape
+            try:
+                new_state_dict[k] = saved_state_dict[k]
+                if saved_state_dict[k].shape != state_dict[k].shape:
+                    logger.warning(
+                        "shape-%s-mismatch. need: %s, get: %s",
+                        k,
+                        state_dict[k].shape,
+                        saved_state_dict[k].shape,
+                    )  #
+                    raise KeyError
+            except:
+                # logger.info(traceback.format_exc())
+                logger.info("%s is not in the checkpoint", k)  # pretrain缺失的
+                new_state_dict[k] = v  # 模型自带的随机值
+        if hasattr(model, "module"):
+            model.module.load_state_dict(new_state_dict, strict=False)
+        else:
+            model.load_state_dict(new_state_dict, strict=False)
+        return model
+
+    go(combd, "combd")
+    model = go(sbd, "sbd")
+    #############
+    logger.info("Loaded model weights")
+
+    iteration = checkpoint_dict["iteration"]
+    learning_rate = checkpoint_dict["learning_rate"]
+    if (
+        optimizer is not None and load_opt == 1
+    ):  ###加载不了，如果是空的的话，重新初始化，可能还会影响lr时间表的更新，因此在train文件最外围catch
+        #   try:
+        optimizer.load_state_dict(checkpoint_dict["optimizer"])
+    #   except:
+    #     traceback.print_exc()
+    logger.info("Loaded checkpoint '{}' (epoch {})".format(checkpoint_path, iteration))
+    return model, optimizer, learning_rate, iteration
+
+
+# def load_checkpoint(checkpoint_path, model, optimizer=None):
+#   assert os.path.isfile(checkpoint_path)
+#   checkpoint_dict = torch.load(checkpoint_path, map_location='cpu')
+#   iteration = checkpoint_dict['iteration']
+#   learning_rate = checkpoint_dict['learning_rate']
+#   if optimizer is not None:
+#     optimizer.load_state_dict(checkpoint_dict['optimizer'])
+#   # print(1111)
+#   saved_state_dict = checkpoint_dict['model']
+#   # print(1111)
+#
+#   if hasattr(model, 'module'):
+#     state_dict = model.module.state_dict()
+#   else:
+#     state_dict = model.state_dict()
+#   new_state_dict= {}
+#   for k, v in state_dict.items():
+#     try:
+#       new_state_dict[k] = saved_state_dict[k]
+#     except:
+#       logger.info("%s is not in the checkpoint" % k)
+#       new_state_dict[k] = v
+#   if hasattr(model, 'module'):
+#     model.module.load_state_dict(new_state_dict)
+#   else:
+#     model.load_state_dict(new_state_dict)
+#   logger.info("Loaded checkpoint '{}' (epoch {})" .format(
+#     checkpoint_path, iteration))
+#   return model, optimizer, learning_rate, iteration
+def load_checkpoint(checkpoint_path, model, optimizer=None, load_opt=1):
+    assert os.path.isfile(checkpoint_path)
+    checkpoint_dict = torch.load(checkpoint_path, map_location="cpu")
+
+    saved_state_dict = checkpoint_dict["model"]
+    if hasattr(model, "module"):
+        state_dict = model.module.state_dict()
+    else:
+        state_dict = model.state_dict()
+    new_state_dict = {}
+    for k, v in state_dict.items():  # 模型需要的shape
+        try:
+            new_state_dict[k] = saved_state_dict[k]
+            if saved_state_dict[k].shape != state_dict[k].shape:
+                logger.warning(
+                    "shape-%s-mismatch|need-%s|get-%s",
+                    k,
+                    state_dict[k].shape,
+                    saved_state_dict[k].shape,
+                )  #
+                raise KeyError
+        except:
+            # logger.info(traceback.format_exc())
+            logger.info("%s is not in the checkpoint", k)  # pretrain缺失的
+            new_state_dict[k] = v  # 模型自带的随机值
+    if hasattr(model, "module"):
+        model.module.load_state_dict(new_state_dict, strict=False)
+    else:
+        model.load_state_dict(new_state_dict, strict=False)
+    logger.info("Loaded model weights")
+
+    iteration = checkpoint_dict["iteration"]
+    learning_rate = checkpoint_dict["learning_rate"]
+    if (
+        optimizer is not None and load_opt == 1
+    ):  ###加载不了，如果是空的的话，重新初始化，可能还会影响lr时间表的更新，因此在train文件最外围catch
+        #   try:
+        optimizer.load_state_dict(checkpoint_dict["optimizer"])
+    #   except:
+    #     traceback.print_exc()
+    logger.info("Loaded checkpoint '{}' (epoch {})".format(checkpoint_path, iteration))
+    return model, optimizer, learning_rate, iteration
+
+
+def save_checkpoint(model, optimizer, learning_rate, iteration, checkpoint_path):
+    logger.info(
+        "Saving model and optimizer state at epoch {} to {}".format(
+            iteration, checkpoint_path
+        )
+    )
+    if hasattr(model, "module"):
+        state_dict = model.module.state_dict()
+    else:
+        state_dict = model.state_dict()
+    torch.save(
+        {
+            "model": state_dict,
+            "iteration": iteration,
+            "optimizer": optimizer.state_dict(),
+            "learning_rate": learning_rate,
+        },
+        checkpoint_path,
+    )
+
+
+def save_checkpoint_d(combd, sbd, optimizer, learning_rate, iteration, checkpoint_path):
+    logger.info(
+        "Saving model and optimizer state at epoch {} to {}".format(
+            iteration, checkpoint_path
+        )
+    )
+    if hasattr(combd, "module"):
+        state_dict_combd = combd.module.state_dict()
+    else:
+        state_dict_combd = combd.state_dict()
+    if hasattr(sbd, "module"):
+        state_dict_sbd = sbd.module.state_dict()
+    else:
+        state_dict_sbd = sbd.state_dict()
+    torch.save(
+        {
+            "combd": state_dict_combd,
+            "sbd": state_dict_sbd,
+            "iteration": iteration,
+            "optimizer": optimizer.state_dict(),
+            "learning_rate": learning_rate,
+        },
+        checkpoint_path,
+    )
+
+
+def summarize(
+    writer,
+    global_step,
+    scalars={},
+    histograms={},
+    images={},
+    audios={},
+    audio_sampling_rate=22050,
+):
+    for k, v in scalars.items():
+        writer.add_scalar(k, v, global_step)
+    for k, v in histograms.items():
+        writer.add_histogram(k, v, global_step)
+    for k, v in images.items():
+        writer.add_image(k, v, global_step, dataformats="HWC")
+    for k, v in audios.items():
+        writer.add_audio(k, v, global_step, audio_sampling_rate)
+
+
+def latest_checkpoint_path(dir_path, regex="G_*.pth"):
+    f_list = glob.glob(os.path.join(dir_path, regex))
+    f_list.sort(key=lambda f: int("".join(filter(str.isdigit, f))))
+    x = f_list[-1]
+    logger.debug(x)
+    return x
+
+
+def plot_spectrogram_to_numpy(spectrogram):
+    global MATPLOTLIB_FLAG
+    if not MATPLOTLIB_FLAG:
+        import matplotlib
+
+        matplotlib.use("Agg")
+        MATPLOTLIB_FLAG = True
+        mpl_logger = logging.getLogger("matplotlib")
+        mpl_logger.setLevel(logging.WARNING)
+    import matplotlib.pylab as plt
+    import numpy as np
+
+    fig, ax = plt.subplots(figsize=(10, 2))
+    im = ax.imshow(spectrogram, aspect="auto", origin="lower", interpolation="none")
+    plt.colorbar(im, ax=ax)
+    plt.xlabel("Frames")
+    plt.ylabel("Channels")
+    plt.tight_layout()
+
+    fig.canvas.draw()
+    data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep="")
+    data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
+    plt.close()
+    return data
+
+
+def plot_alignment_to_numpy(alignment, info=None):
+    global MATPLOTLIB_FLAG
+    if not MATPLOTLIB_FLAG:
+        import matplotlib
+
+        matplotlib.use("Agg")
+        MATPLOTLIB_FLAG = True
+        mpl_logger = logging.getLogger("matplotlib")
+        mpl_logger.setLevel(logging.WARNING)
+    import matplotlib.pylab as plt
+    import numpy as np
+
+    fig, ax = plt.subplots(figsize=(6, 4))
+    im = ax.imshow(
+        alignment.transpose(), aspect="auto", origin="lower", interpolation="none"
+    )
+    fig.colorbar(im, ax=ax)
+    xlabel = "Decoder timestep"
+    if info is not None:
+        xlabel += "\n\n" + info
+    plt.xlabel(xlabel)
+    plt.ylabel("Encoder timestep")
+    plt.tight_layout()
+
+    fig.canvas.draw()
+    data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep="")
+    data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
+    plt.close()
+    return data
+
+
+def load_wav_to_torch(full_path):
+    sampling_rate, data = read(full_path)
+    return torch.FloatTensor(data.astype(np.float32)), sampling_rate
+
+
+def load_filepaths_and_text(filename, split="|"):
+    with open(filename, encoding="utf-8") as f:
+        filepaths_and_text = [line.strip().split(split) for line in f]
+    return filepaths_and_text
+
+
+def get_hparams(init=True):
+    """
+    todo:
+      结尾七人组：
+        保存频率、总epoch                     done
+        bs                                    done
+        pretrainG、pretrainD                  done
+        卡号：os.en["CUDA_VISIBLE_DEVICES"]   done
+        if_latest                             done
+      模型：if_f0                             done
+      采样率：自动选择config                  done
+      是否缓存数据集进GPU:if_cache_data_in_gpu done
+
+      -m:
+        自动决定training_files路径,改掉train_nsf_load_pretrain.py里的hps.data.training_files    done
+      -c不要了
+    """
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "-se",
+        "--save_every_epoch",
+        type=int,
+        required=True,
+        help="checkpoint save frequency (epoch)",
+    )
+    parser.add_argument(
+        "-te", "--total_epoch", type=int, required=True, help="total_epoch"
+    )
+    parser.add_argument(
+        "-pg", "--pretrainG", type=str, default="", help="Pretrained Discriminator path"
+    )
+    parser.add_argument(
+        "-pd", "--pretrainD", type=str, default="", help="Pretrained Generator path"
+    )
+    parser.add_argument("-g", "--gpus", type=str, default="0", help="split by -")
+    parser.add_argument(
+        "-bs", "--batch_size", type=int, required=True, help="batch size"
+    )
+    parser.add_argument(
+        "-e", "--experiment_dir", type=str, required=True, help="experiment dir"
+    )  # -m
+    parser.add_argument(
+        "-sr", "--sample_rate", type=str, required=True, help="sample rate, 32k/40k/48k"
+    )
+    parser.add_argument(
+        "-sw",
+        "--save_every_weights",
+        type=str,
+        default="0",
+        help="save the extracted model in weights directory when saving checkpoints",
+    )
+    parser.add_argument(
+        "-v", "--version", type=str, required=True, help="model version"
+    )
+    parser.add_argument(
+        "-f0",
+        "--if_f0",
+        type=int,
+        required=True,
+        help="use f0 as one of the inputs of the model, 1 or 0",
+    )
+    parser.add_argument(
+        "-l",
+        "--if_latest",
+        type=int,
+        required=True,
+        help="if only save the latest G/D pth file, 1 or 0",
+    )
+    parser.add_argument(
+        "-c",
+        "--if_cache_data_in_gpu",
+        type=int,
+        required=True,
+        help="if caching the dataset in GPU memory, 1 or 0",
+    )
+
+    args = parser.parse_args()
+    name = args.experiment_dir
+    experiment_dir = os.path.join("./logs", args.experiment_dir)
+
+    config_save_path = os.path.join(experiment_dir, "config.json")
+    with open(config_save_path, "r") as f:
+        config = json.load(f)
+
+    hparams = HParams(**config)
+    hparams.model_dir = hparams.experiment_dir = experiment_dir
+    hparams.save_every_epoch = args.save_every_epoch
+    hparams.name = name
+    hparams.total_epoch = args.total_epoch
+    hparams.pretrainG = args.pretrainG
+    hparams.pretrainD = args.pretrainD
+    hparams.version = args.version
+    hparams.gpus = args.gpus
+    hparams.train.batch_size = args.batch_size
+    hparams.sample_rate = args.sample_rate
+    hparams.if_f0 = args.if_f0
+    hparams.if_latest = args.if_latest
+    hparams.save_every_weights = args.save_every_weights
+    hparams.if_cache_data_in_gpu = args.if_cache_data_in_gpu
+    hparams.data.training_files = "%s/filelist.txt" % experiment_dir
+    return hparams
+
+
+def get_hparams_from_dir(model_dir):
+    config_save_path = os.path.join(model_dir, "config.json")
+    with open(config_save_path, "r") as f:
+        data = f.read()
+    config = json.loads(data)
+
+    hparams = HParams(**config)
+    hparams.model_dir = model_dir
+    return hparams
+
+
+def get_hparams_from_file(config_path):
+    with open(config_path, "r") as f:
+        data = f.read()
+    config = json.loads(data)
+
+    hparams = HParams(**config)
+    return hparams
+
+
+def check_git_hash(model_dir):
+    source_dir = os.path.dirname(os.path.realpath(__file__))
+    if not os.path.exists(os.path.join(source_dir, ".git")):
+        logger.warning(
+            "{} is not a git repository, therefore hash value comparison will be ignored.".format(
+                source_dir
+            )
+        )
+        return
+
+    cur_hash = subprocess.getoutput("git rev-parse HEAD")
+
+    path = os.path.join(model_dir, "githash")
+    if os.path.exists(path):
+        saved_hash = open(path).read()
+        if saved_hash != cur_hash:
+            logger.warning(
+                "git hash values are different. {}(saved) != {}(current)".format(
+                    saved_hash[:8], cur_hash[:8]
+                )
+            )
+    else:
+        open(path, "w").write(cur_hash)
+
+
+def get_logger(model_dir, filename="train.log"):
+    global logger
+    logger = logging.getLogger(os.path.basename(model_dir))
+    logger.setLevel(logging.DEBUG)
+
+    formatter = logging.Formatter("%(asctime)s\t%(name)s\t%(levelname)s\t%(message)s")
+    if not os.path.exists(model_dir):
+        os.makedirs(model_dir)
+    h = logging.FileHandler(os.path.join(model_dir, filename))
+    h.setLevel(logging.DEBUG)
+    h.setFormatter(formatter)
+    logger.addHandler(h)
+    return logger
+
+
+class HParams:
+    def __init__(self, **kwargs):
+        for k, v in kwargs.items():
+            if type(v) == dict:
+                v = HParams(**v)
+            self[k] = v
+
+    def keys(self):
+        return self.__dict__.keys()
+
+    def items(self):
+        return self.__dict__.items()
+
+    def values(self):
+        return self.__dict__.values()
+
+    def __len__(self):
+        return len(self.__dict__)
+
+    def __getitem__(self, key):
+        return getattr(self, key)
+
+    def __setitem__(self, key, value):
+        return setattr(self, key, value)
+
+    def __contains__(self, key):
+        return key in self.__dict__
+
+    def __repr__(self):
+        return self.__dict__.__repr__()
diff --git a/rvc/lib/uvr5_pack/lib_v5/dataset.py b/rvc/lib/uvr5_pack/lib_v5/dataset.py
new file mode 100644
index 0000000000000000000000000000000000000000..cfd01a174978d97180a897e40cb59ecadec1d12e
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/dataset.py
@@ -0,0 +1,183 @@
+import os
+import random
+
+import numpy as np
+import torch
+import torch.utils.data
+from tqdm import tqdm
+
+from . import spec_utils
+
+
+class VocalRemoverValidationSet(torch.utils.data.Dataset):
+    def __init__(self, patch_list):
+        self.patch_list = patch_list
+
+    def __len__(self):
+        return len(self.patch_list)
+
+    def __getitem__(self, idx):
+        path = self.patch_list[idx]
+        data = np.load(path)
+
+        X, y = data["X"], data["y"]
+
+        X_mag = np.abs(X)
+        y_mag = np.abs(y)
+
+        return X_mag, y_mag
+
+
+def make_pair(mix_dir, inst_dir):
+    input_exts = [".wav", ".m4a", ".mp3", ".mp4", ".flac"]
+
+    X_list = sorted(
+        [
+            os.path.join(mix_dir, fname)
+            for fname in os.listdir(mix_dir)
+            if os.path.splitext(fname)[1] in input_exts
+        ]
+    )
+    y_list = sorted(
+        [
+            os.path.join(inst_dir, fname)
+            for fname in os.listdir(inst_dir)
+            if os.path.splitext(fname)[1] in input_exts
+        ]
+    )
+
+    filelist = list(zip(X_list, y_list))
+
+    return filelist
+
+
+def train_val_split(dataset_dir, split_mode, val_rate, val_filelist):
+    if split_mode == "random":
+        filelist = make_pair(
+            os.path.join(dataset_dir, "mixtures"),
+            os.path.join(dataset_dir, "instruments"),
+        )
+
+        random.shuffle(filelist)
+
+        if len(val_filelist) == 0:
+            val_size = int(len(filelist) * val_rate)
+            train_filelist = filelist[:-val_size]
+            val_filelist = filelist[-val_size:]
+        else:
+            train_filelist = [
+                pair for pair in filelist if list(pair) not in val_filelist
+            ]
+    elif split_mode == "subdirs":
+        if len(val_filelist) != 0:
+            raise ValueError(
+                "The `val_filelist` option is not available in `subdirs` mode"
+            )
+
+        train_filelist = make_pair(
+            os.path.join(dataset_dir, "training/mixtures"),
+            os.path.join(dataset_dir, "training/instruments"),
+        )
+
+        val_filelist = make_pair(
+            os.path.join(dataset_dir, "validation/mixtures"),
+            os.path.join(dataset_dir, "validation/instruments"),
+        )
+
+    return train_filelist, val_filelist
+
+
+def augment(X, y, reduction_rate, reduction_mask, mixup_rate, mixup_alpha):
+    perm = np.random.permutation(len(X))
+    for i, idx in enumerate(tqdm(perm)):
+        if np.random.uniform() < reduction_rate:
+            y[idx] = spec_utils.reduce_vocal_aggressively(
+                X[idx], y[idx], reduction_mask
+            )
+
+        if np.random.uniform() < 0.5:
+            # swap channel
+            X[idx] = X[idx, ::-1]
+            y[idx] = y[idx, ::-1]
+        if np.random.uniform() < 0.02:
+            # mono
+            X[idx] = X[idx].mean(axis=0, keepdims=True)
+            y[idx] = y[idx].mean(axis=0, keepdims=True)
+        if np.random.uniform() < 0.02:
+            # inst
+            X[idx] = y[idx]
+
+        if np.random.uniform() < mixup_rate and i < len(perm) - 1:
+            lam = np.random.beta(mixup_alpha, mixup_alpha)
+            X[idx] = lam * X[idx] + (1 - lam) * X[perm[i + 1]]
+            y[idx] = lam * y[idx] + (1 - lam) * y[perm[i + 1]]
+
+    return X, y
+
+
+def make_padding(width, cropsize, offset):
+    left = offset
+    roi_size = cropsize - left * 2
+    if roi_size == 0:
+        roi_size = cropsize
+    right = roi_size - (width % roi_size) + left
+
+    return left, right, roi_size
+
+
+def make_training_set(filelist, cropsize, patches, sr, hop_length, n_fft, offset):
+    len_dataset = patches * len(filelist)
+
+    X_dataset = np.zeros((len_dataset, 2, n_fft // 2 + 1, cropsize), dtype=np.complex64)
+    y_dataset = np.zeros((len_dataset, 2, n_fft // 2 + 1, cropsize), dtype=np.complex64)
+
+    for i, (X_path, y_path) in enumerate(tqdm(filelist)):
+        X, y = spec_utils.cache_or_load(X_path, y_path, sr, hop_length, n_fft)
+        coef = np.max([np.abs(X).max(), np.abs(y).max()])
+        X, y = X / coef, y / coef
+
+        l, r, roi_size = make_padding(X.shape[2], cropsize, offset)
+        X_pad = np.pad(X, ((0, 0), (0, 0), (l, r)), mode="constant")
+        y_pad = np.pad(y, ((0, 0), (0, 0), (l, r)), mode="constant")
+
+        starts = np.random.randint(0, X_pad.shape[2] - cropsize, patches)
+        ends = starts + cropsize
+        for j in range(patches):
+            idx = i * patches + j
+            X_dataset[idx] = X_pad[:, :, starts[j] : ends[j]]
+            y_dataset[idx] = y_pad[:, :, starts[j] : ends[j]]
+
+    return X_dataset, y_dataset
+
+
+def make_validation_set(filelist, cropsize, sr, hop_length, n_fft, offset):
+    patch_list = []
+    patch_dir = "cs{}_sr{}_hl{}_nf{}_of{}".format(
+        cropsize, sr, hop_length, n_fft, offset
+    )
+    os.makedirs(patch_dir, exist_ok=True)
+
+    for i, (X_path, y_path) in enumerate(tqdm(filelist)):
+        basename = os.path.splitext(os.path.basename(X_path))[0]
+
+        X, y = spec_utils.cache_or_load(X_path, y_path, sr, hop_length, n_fft)
+        coef = np.max([np.abs(X).max(), np.abs(y).max()])
+        X, y = X / coef, y / coef
+
+        l, r, roi_size = make_padding(X.shape[2], cropsize, offset)
+        X_pad = np.pad(X, ((0, 0), (0, 0), (l, r)), mode="constant")
+        y_pad = np.pad(y, ((0, 0), (0, 0), (l, r)), mode="constant")
+
+        len_dataset = int(np.ceil(X.shape[2] / roi_size))
+        for j in range(len_dataset):
+            outpath = os.path.join(patch_dir, "{}_p{}.npz".format(basename, j))
+            start = j * roi_size
+            if not os.path.exists(outpath):
+                np.savez(
+                    outpath,
+                    X=X_pad[:, :, start : start + cropsize],
+                    y=y_pad[:, :, start : start + cropsize],
+                )
+            patch_list.append(outpath)
+
+    return VocalRemoverValidationSet(patch_list)
diff --git a/rvc/lib/uvr5_pack/lib_v5/layers.py b/rvc/lib/uvr5_pack/lib_v5/layers.py
new file mode 100644
index 0000000000000000000000000000000000000000..4fc1b5cb85a3327f60cbb9f5deffbeeaaac516ad
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/layers.py
@@ -0,0 +1,118 @@
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from . import spec_utils
+
+
+class Conv2DBNActiv(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+        super(Conv2DBNActiv, self).__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(
+                nin,
+                nout,
+                kernel_size=ksize,
+                stride=stride,
+                padding=pad,
+                dilation=dilation,
+                bias=False,
+            ),
+            nn.BatchNorm2d(nout),
+            activ(),
+        )
+
+    def __call__(self, x):
+        return self.conv(x)
+
+
+class SeperableConv2DBNActiv(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+        super(SeperableConv2DBNActiv, self).__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(
+                nin,
+                nin,
+                kernel_size=ksize,
+                stride=stride,
+                padding=pad,
+                dilation=dilation,
+                groups=nin,
+                bias=False,
+            ),
+            nn.Conv2d(nin, nout, kernel_size=1, bias=False),
+            nn.BatchNorm2d(nout),
+            activ(),
+        )
+
+    def __call__(self, x):
+        return self.conv(x)
+
+
+class Encoder(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU):
+        super(Encoder, self).__init__()
+        self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+        self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ)
+
+    def __call__(self, x):
+        skip = self.conv1(x)
+        h = self.conv2(skip)
+
+        return h, skip
+
+
+class Decoder(nn.Module):
+    def __init__(
+        self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
+    ):
+        super(Decoder, self).__init__()
+        self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+        self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+    def __call__(self, x, skip=None):
+        x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True)
+        if skip is not None:
+            skip = spec_utils.crop_center(skip, x)
+            x = torch.cat([x, skip], dim=1)
+        h = self.conv(x)
+
+        if self.dropout is not None:
+            h = self.dropout(h)
+
+        return h
+
+
+class ASPPModule(nn.Module):
+    def __init__(self, nin, nout, dilations=(4, 8, 16), activ=nn.ReLU):
+        super(ASPPModule, self).__init__()
+        self.conv1 = nn.Sequential(
+            nn.AdaptiveAvgPool2d((1, None)),
+            Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ),
+        )
+        self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ)
+        self.conv3 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[0], dilations[0], activ=activ
+        )
+        self.conv4 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[1], dilations[1], activ=activ
+        )
+        self.conv5 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+        )
+        self.bottleneck = nn.Sequential(
+            Conv2DBNActiv(nin * 5, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1)
+        )
+
+    def forward(self, x):
+        _, _, h, w = x.size()
+        feat1 = F.interpolate(
+            self.conv1(x), size=(h, w), mode="bilinear", align_corners=True
+        )
+        feat2 = self.conv2(x)
+        feat3 = self.conv3(x)
+        feat4 = self.conv4(x)
+        feat5 = self.conv5(x)
+        out = torch.cat((feat1, feat2, feat3, feat4, feat5), dim=1)
+        bottle = self.bottleneck(out)
+        return bottle
diff --git a/rvc/lib/uvr5_pack/lib_v5/layers_123812KB .py b/rvc/lib/uvr5_pack/lib_v5/layers_123812KB .py
new file mode 100644
index 0000000000000000000000000000000000000000..4fc1b5cb85a3327f60cbb9f5deffbeeaaac516ad
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/layers_123812KB .py	
@@ -0,0 +1,118 @@
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from . import spec_utils
+
+
+class Conv2DBNActiv(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+        super(Conv2DBNActiv, self).__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(
+                nin,
+                nout,
+                kernel_size=ksize,
+                stride=stride,
+                padding=pad,
+                dilation=dilation,
+                bias=False,
+            ),
+            nn.BatchNorm2d(nout),
+            activ(),
+        )
+
+    def __call__(self, x):
+        return self.conv(x)
+
+
+class SeperableConv2DBNActiv(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+        super(SeperableConv2DBNActiv, self).__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(
+                nin,
+                nin,
+                kernel_size=ksize,
+                stride=stride,
+                padding=pad,
+                dilation=dilation,
+                groups=nin,
+                bias=False,
+            ),
+            nn.Conv2d(nin, nout, kernel_size=1, bias=False),
+            nn.BatchNorm2d(nout),
+            activ(),
+        )
+
+    def __call__(self, x):
+        return self.conv(x)
+
+
+class Encoder(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU):
+        super(Encoder, self).__init__()
+        self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+        self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ)
+
+    def __call__(self, x):
+        skip = self.conv1(x)
+        h = self.conv2(skip)
+
+        return h, skip
+
+
+class Decoder(nn.Module):
+    def __init__(
+        self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
+    ):
+        super(Decoder, self).__init__()
+        self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+        self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+    def __call__(self, x, skip=None):
+        x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True)
+        if skip is not None:
+            skip = spec_utils.crop_center(skip, x)
+            x = torch.cat([x, skip], dim=1)
+        h = self.conv(x)
+
+        if self.dropout is not None:
+            h = self.dropout(h)
+
+        return h
+
+
+class ASPPModule(nn.Module):
+    def __init__(self, nin, nout, dilations=(4, 8, 16), activ=nn.ReLU):
+        super(ASPPModule, self).__init__()
+        self.conv1 = nn.Sequential(
+            nn.AdaptiveAvgPool2d((1, None)),
+            Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ),
+        )
+        self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ)
+        self.conv3 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[0], dilations[0], activ=activ
+        )
+        self.conv4 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[1], dilations[1], activ=activ
+        )
+        self.conv5 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+        )
+        self.bottleneck = nn.Sequential(
+            Conv2DBNActiv(nin * 5, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1)
+        )
+
+    def forward(self, x):
+        _, _, h, w = x.size()
+        feat1 = F.interpolate(
+            self.conv1(x), size=(h, w), mode="bilinear", align_corners=True
+        )
+        feat2 = self.conv2(x)
+        feat3 = self.conv3(x)
+        feat4 = self.conv4(x)
+        feat5 = self.conv5(x)
+        out = torch.cat((feat1, feat2, feat3, feat4, feat5), dim=1)
+        bottle = self.bottleneck(out)
+        return bottle
diff --git a/rvc/lib/uvr5_pack/lib_v5/layers_123821KB.py b/rvc/lib/uvr5_pack/lib_v5/layers_123821KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..4fc1b5cb85a3327f60cbb9f5deffbeeaaac516ad
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/layers_123821KB.py
@@ -0,0 +1,118 @@
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from . import spec_utils
+
+
+class Conv2DBNActiv(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+        super(Conv2DBNActiv, self).__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(
+                nin,
+                nout,
+                kernel_size=ksize,
+                stride=stride,
+                padding=pad,
+                dilation=dilation,
+                bias=False,
+            ),
+            nn.BatchNorm2d(nout),
+            activ(),
+        )
+
+    def __call__(self, x):
+        return self.conv(x)
+
+
+class SeperableConv2DBNActiv(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+        super(SeperableConv2DBNActiv, self).__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(
+                nin,
+                nin,
+                kernel_size=ksize,
+                stride=stride,
+                padding=pad,
+                dilation=dilation,
+                groups=nin,
+                bias=False,
+            ),
+            nn.Conv2d(nin, nout, kernel_size=1, bias=False),
+            nn.BatchNorm2d(nout),
+            activ(),
+        )
+
+    def __call__(self, x):
+        return self.conv(x)
+
+
+class Encoder(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU):
+        super(Encoder, self).__init__()
+        self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+        self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ)
+
+    def __call__(self, x):
+        skip = self.conv1(x)
+        h = self.conv2(skip)
+
+        return h, skip
+
+
+class Decoder(nn.Module):
+    def __init__(
+        self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
+    ):
+        super(Decoder, self).__init__()
+        self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+        self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+    def __call__(self, x, skip=None):
+        x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True)
+        if skip is not None:
+            skip = spec_utils.crop_center(skip, x)
+            x = torch.cat([x, skip], dim=1)
+        h = self.conv(x)
+
+        if self.dropout is not None:
+            h = self.dropout(h)
+
+        return h
+
+
+class ASPPModule(nn.Module):
+    def __init__(self, nin, nout, dilations=(4, 8, 16), activ=nn.ReLU):
+        super(ASPPModule, self).__init__()
+        self.conv1 = nn.Sequential(
+            nn.AdaptiveAvgPool2d((1, None)),
+            Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ),
+        )
+        self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ)
+        self.conv3 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[0], dilations[0], activ=activ
+        )
+        self.conv4 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[1], dilations[1], activ=activ
+        )
+        self.conv5 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+        )
+        self.bottleneck = nn.Sequential(
+            Conv2DBNActiv(nin * 5, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1)
+        )
+
+    def forward(self, x):
+        _, _, h, w = x.size()
+        feat1 = F.interpolate(
+            self.conv1(x), size=(h, w), mode="bilinear", align_corners=True
+        )
+        feat2 = self.conv2(x)
+        feat3 = self.conv3(x)
+        feat4 = self.conv4(x)
+        feat5 = self.conv5(x)
+        out = torch.cat((feat1, feat2, feat3, feat4, feat5), dim=1)
+        bottle = self.bottleneck(out)
+        return bottle
diff --git a/rvc/lib/uvr5_pack/lib_v5/layers_33966KB.py b/rvc/lib/uvr5_pack/lib_v5/layers_33966KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..9b127bc6427f5c60c8cf85603a3d8a093c3501c4
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/layers_33966KB.py
@@ -0,0 +1,126 @@
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from . import spec_utils
+
+
+class Conv2DBNActiv(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+        super(Conv2DBNActiv, self).__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(
+                nin,
+                nout,
+                kernel_size=ksize,
+                stride=stride,
+                padding=pad,
+                dilation=dilation,
+                bias=False,
+            ),
+            nn.BatchNorm2d(nout),
+            activ(),
+        )
+
+    def __call__(self, x):
+        return self.conv(x)
+
+
+class SeperableConv2DBNActiv(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+        super(SeperableConv2DBNActiv, self).__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(
+                nin,
+                nin,
+                kernel_size=ksize,
+                stride=stride,
+                padding=pad,
+                dilation=dilation,
+                groups=nin,
+                bias=False,
+            ),
+            nn.Conv2d(nin, nout, kernel_size=1, bias=False),
+            nn.BatchNorm2d(nout),
+            activ(),
+        )
+
+    def __call__(self, x):
+        return self.conv(x)
+
+
+class Encoder(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU):
+        super(Encoder, self).__init__()
+        self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+        self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ)
+
+    def __call__(self, x):
+        skip = self.conv1(x)
+        h = self.conv2(skip)
+
+        return h, skip
+
+
+class Decoder(nn.Module):
+    def __init__(
+        self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
+    ):
+        super(Decoder, self).__init__()
+        self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+        self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+    def __call__(self, x, skip=None):
+        x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True)
+        if skip is not None:
+            skip = spec_utils.crop_center(skip, x)
+            x = torch.cat([x, skip], dim=1)
+        h = self.conv(x)
+
+        if self.dropout is not None:
+            h = self.dropout(h)
+
+        return h
+
+
+class ASPPModule(nn.Module):
+    def __init__(self, nin, nout, dilations=(4, 8, 16, 32, 64), activ=nn.ReLU):
+        super(ASPPModule, self).__init__()
+        self.conv1 = nn.Sequential(
+            nn.AdaptiveAvgPool2d((1, None)),
+            Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ),
+        )
+        self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ)
+        self.conv3 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[0], dilations[0], activ=activ
+        )
+        self.conv4 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[1], dilations[1], activ=activ
+        )
+        self.conv5 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+        )
+        self.conv6 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+        )
+        self.conv7 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+        )
+        self.bottleneck = nn.Sequential(
+            Conv2DBNActiv(nin * 7, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1)
+        )
+
+    def forward(self, x):
+        _, _, h, w = x.size()
+        feat1 = F.interpolate(
+            self.conv1(x), size=(h, w), mode="bilinear", align_corners=True
+        )
+        feat2 = self.conv2(x)
+        feat3 = self.conv3(x)
+        feat4 = self.conv4(x)
+        feat5 = self.conv5(x)
+        feat6 = self.conv6(x)
+        feat7 = self.conv7(x)
+        out = torch.cat((feat1, feat2, feat3, feat4, feat5, feat6, feat7), dim=1)
+        bottle = self.bottleneck(out)
+        return bottle
diff --git a/rvc/lib/uvr5_pack/lib_v5/layers_537227KB.py b/rvc/lib/uvr5_pack/lib_v5/layers_537227KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..9b127bc6427f5c60c8cf85603a3d8a093c3501c4
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/layers_537227KB.py
@@ -0,0 +1,126 @@
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from . import spec_utils
+
+
+class Conv2DBNActiv(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+        super(Conv2DBNActiv, self).__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(
+                nin,
+                nout,
+                kernel_size=ksize,
+                stride=stride,
+                padding=pad,
+                dilation=dilation,
+                bias=False,
+            ),
+            nn.BatchNorm2d(nout),
+            activ(),
+        )
+
+    def __call__(self, x):
+        return self.conv(x)
+
+
+class SeperableConv2DBNActiv(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+        super(SeperableConv2DBNActiv, self).__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(
+                nin,
+                nin,
+                kernel_size=ksize,
+                stride=stride,
+                padding=pad,
+                dilation=dilation,
+                groups=nin,
+                bias=False,
+            ),
+            nn.Conv2d(nin, nout, kernel_size=1, bias=False),
+            nn.BatchNorm2d(nout),
+            activ(),
+        )
+
+    def __call__(self, x):
+        return self.conv(x)
+
+
+class Encoder(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU):
+        super(Encoder, self).__init__()
+        self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+        self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ)
+
+    def __call__(self, x):
+        skip = self.conv1(x)
+        h = self.conv2(skip)
+
+        return h, skip
+
+
+class Decoder(nn.Module):
+    def __init__(
+        self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
+    ):
+        super(Decoder, self).__init__()
+        self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+        self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+    def __call__(self, x, skip=None):
+        x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True)
+        if skip is not None:
+            skip = spec_utils.crop_center(skip, x)
+            x = torch.cat([x, skip], dim=1)
+        h = self.conv(x)
+
+        if self.dropout is not None:
+            h = self.dropout(h)
+
+        return h
+
+
+class ASPPModule(nn.Module):
+    def __init__(self, nin, nout, dilations=(4, 8, 16, 32, 64), activ=nn.ReLU):
+        super(ASPPModule, self).__init__()
+        self.conv1 = nn.Sequential(
+            nn.AdaptiveAvgPool2d((1, None)),
+            Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ),
+        )
+        self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ)
+        self.conv3 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[0], dilations[0], activ=activ
+        )
+        self.conv4 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[1], dilations[1], activ=activ
+        )
+        self.conv5 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+        )
+        self.conv6 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+        )
+        self.conv7 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+        )
+        self.bottleneck = nn.Sequential(
+            Conv2DBNActiv(nin * 7, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1)
+        )
+
+    def forward(self, x):
+        _, _, h, w = x.size()
+        feat1 = F.interpolate(
+            self.conv1(x), size=(h, w), mode="bilinear", align_corners=True
+        )
+        feat2 = self.conv2(x)
+        feat3 = self.conv3(x)
+        feat4 = self.conv4(x)
+        feat5 = self.conv5(x)
+        feat6 = self.conv6(x)
+        feat7 = self.conv7(x)
+        out = torch.cat((feat1, feat2, feat3, feat4, feat5, feat6, feat7), dim=1)
+        bottle = self.bottleneck(out)
+        return bottle
diff --git a/rvc/lib/uvr5_pack/lib_v5/layers_537238KB.py b/rvc/lib/uvr5_pack/lib_v5/layers_537238KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..9b127bc6427f5c60c8cf85603a3d8a093c3501c4
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/layers_537238KB.py
@@ -0,0 +1,126 @@
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from . import spec_utils
+
+
+class Conv2DBNActiv(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+        super(Conv2DBNActiv, self).__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(
+                nin,
+                nout,
+                kernel_size=ksize,
+                stride=stride,
+                padding=pad,
+                dilation=dilation,
+                bias=False,
+            ),
+            nn.BatchNorm2d(nout),
+            activ(),
+        )
+
+    def __call__(self, x):
+        return self.conv(x)
+
+
+class SeperableConv2DBNActiv(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+        super(SeperableConv2DBNActiv, self).__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(
+                nin,
+                nin,
+                kernel_size=ksize,
+                stride=stride,
+                padding=pad,
+                dilation=dilation,
+                groups=nin,
+                bias=False,
+            ),
+            nn.Conv2d(nin, nout, kernel_size=1, bias=False),
+            nn.BatchNorm2d(nout),
+            activ(),
+        )
+
+    def __call__(self, x):
+        return self.conv(x)
+
+
+class Encoder(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU):
+        super(Encoder, self).__init__()
+        self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+        self.conv2 = Conv2DBNActiv(nout, nout, ksize, stride, pad, activ=activ)
+
+    def __call__(self, x):
+        skip = self.conv1(x)
+        h = self.conv2(skip)
+
+        return h, skip
+
+
+class Decoder(nn.Module):
+    def __init__(
+        self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
+    ):
+        super(Decoder, self).__init__()
+        self.conv = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+        self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+    def __call__(self, x, skip=None):
+        x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True)
+        if skip is not None:
+            skip = spec_utils.crop_center(skip, x)
+            x = torch.cat([x, skip], dim=1)
+        h = self.conv(x)
+
+        if self.dropout is not None:
+            h = self.dropout(h)
+
+        return h
+
+
+class ASPPModule(nn.Module):
+    def __init__(self, nin, nout, dilations=(4, 8, 16, 32, 64), activ=nn.ReLU):
+        super(ASPPModule, self).__init__()
+        self.conv1 = nn.Sequential(
+            nn.AdaptiveAvgPool2d((1, None)),
+            Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ),
+        )
+        self.conv2 = Conv2DBNActiv(nin, nin, 1, 1, 0, activ=activ)
+        self.conv3 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[0], dilations[0], activ=activ
+        )
+        self.conv4 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[1], dilations[1], activ=activ
+        )
+        self.conv5 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+        )
+        self.conv6 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+        )
+        self.conv7 = SeperableConv2DBNActiv(
+            nin, nin, 3, 1, dilations[2], dilations[2], activ=activ
+        )
+        self.bottleneck = nn.Sequential(
+            Conv2DBNActiv(nin * 7, nout, 1, 1, 0, activ=activ), nn.Dropout2d(0.1)
+        )
+
+    def forward(self, x):
+        _, _, h, w = x.size()
+        feat1 = F.interpolate(
+            self.conv1(x), size=(h, w), mode="bilinear", align_corners=True
+        )
+        feat2 = self.conv2(x)
+        feat3 = self.conv3(x)
+        feat4 = self.conv4(x)
+        feat5 = self.conv5(x)
+        feat6 = self.conv6(x)
+        feat7 = self.conv7(x)
+        out = torch.cat((feat1, feat2, feat3, feat4, feat5, feat6, feat7), dim=1)
+        bottle = self.bottleneck(out)
+        return bottle
diff --git a/rvc/lib/uvr5_pack/lib_v5/layers_new.py b/rvc/lib/uvr5_pack/lib_v5/layers_new.py
new file mode 100644
index 0000000000000000000000000000000000000000..44153b6a23399c6938affc61c71919eaa172bcee
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/layers_new.py
@@ -0,0 +1,125 @@
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from . import spec_utils
+
+
+class Conv2DBNActiv(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, dilation=1, activ=nn.ReLU):
+        super(Conv2DBNActiv, self).__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(
+                nin,
+                nout,
+                kernel_size=ksize,
+                stride=stride,
+                padding=pad,
+                dilation=dilation,
+                bias=False,
+            ),
+            nn.BatchNorm2d(nout),
+            activ(),
+        )
+
+    def __call__(self, x):
+        return self.conv(x)
+
+
+class Encoder(nn.Module):
+    def __init__(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU):
+        super(Encoder, self).__init__()
+        self.conv1 = Conv2DBNActiv(nin, nout, ksize, stride, pad, activ=activ)
+        self.conv2 = Conv2DBNActiv(nout, nout, ksize, 1, pad, activ=activ)
+
+    def __call__(self, x):
+        h = self.conv1(x)
+        h = self.conv2(h)
+
+        return h
+
+
+class Decoder(nn.Module):
+    def __init__(
+        self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.ReLU, dropout=False
+    ):
+        super(Decoder, self).__init__()
+        self.conv1 = Conv2DBNActiv(nin, nout, ksize, 1, pad, activ=activ)
+        # self.conv2 = Conv2DBNActiv(nout, nout, ksize, 1, pad, activ=activ)
+        self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+    def __call__(self, x, skip=None):
+        x = F.interpolate(x, scale_factor=2, mode="bilinear", align_corners=True)
+
+        if skip is not None:
+            skip = spec_utils.crop_center(skip, x)
+            x = torch.cat([x, skip], dim=1)
+
+        h = self.conv1(x)
+        # h = self.conv2(h)
+
+        if self.dropout is not None:
+            h = self.dropout(h)
+
+        return h
+
+
+class ASPPModule(nn.Module):
+    def __init__(self, nin, nout, dilations=(4, 8, 12), activ=nn.ReLU, dropout=False):
+        super(ASPPModule, self).__init__()
+        self.conv1 = nn.Sequential(
+            nn.AdaptiveAvgPool2d((1, None)),
+            Conv2DBNActiv(nin, nout, 1, 1, 0, activ=activ),
+        )
+        self.conv2 = Conv2DBNActiv(nin, nout, 1, 1, 0, activ=activ)
+        self.conv3 = Conv2DBNActiv(
+            nin, nout, 3, 1, dilations[0], dilations[0], activ=activ
+        )
+        self.conv4 = Conv2DBNActiv(
+            nin, nout, 3, 1, dilations[1], dilations[1], activ=activ
+        )
+        self.conv5 = Conv2DBNActiv(
+            nin, nout, 3, 1, dilations[2], dilations[2], activ=activ
+        )
+        self.bottleneck = Conv2DBNActiv(nout * 5, nout, 1, 1, 0, activ=activ)
+        self.dropout = nn.Dropout2d(0.1) if dropout else None
+
+    def forward(self, x):
+        _, _, h, w = x.size()
+        feat1 = F.interpolate(
+            self.conv1(x), size=(h, w), mode="bilinear", align_corners=True
+        )
+        feat2 = self.conv2(x)
+        feat3 = self.conv3(x)
+        feat4 = self.conv4(x)
+        feat5 = self.conv5(x)
+        out = torch.cat((feat1, feat2, feat3, feat4, feat5), dim=1)
+        out = self.bottleneck(out)
+
+        if self.dropout is not None:
+            out = self.dropout(out)
+
+        return out
+
+
+class LSTMModule(nn.Module):
+    def __init__(self, nin_conv, nin_lstm, nout_lstm):
+        super(LSTMModule, self).__init__()
+        self.conv = Conv2DBNActiv(nin_conv, 1, 1, 1, 0)
+        self.lstm = nn.LSTM(
+            input_size=nin_lstm, hidden_size=nout_lstm // 2, bidirectional=True
+        )
+        self.dense = nn.Sequential(
+            nn.Linear(nout_lstm, nin_lstm), nn.BatchNorm1d(nin_lstm), nn.ReLU()
+        )
+
+    def forward(self, x):
+        N, _, nbins, nframes = x.size()
+        h = self.conv(x)[:, 0]  # N, nbins, nframes
+        h = h.permute(2, 0, 1)  # nframes, N, nbins
+        h, _ = self.lstm(h)
+        h = self.dense(h.reshape(-1, h.size()[-1]))  # nframes * N, nbins
+        h = h.reshape(nframes, N, 1, nbins)
+        h = h.permute(1, 2, 3, 0)
+
+        return h
diff --git a/rvc/lib/uvr5_pack/lib_v5/model_param_init.py b/rvc/lib/uvr5_pack/lib_v5/model_param_init.py
new file mode 100644
index 0000000000000000000000000000000000000000..b995c0bfb1194746187692e2ab1c2a6dbaaaec6c
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/model_param_init.py
@@ -0,0 +1,69 @@
+import json
+import os
+import pathlib
+
+default_param = {}
+default_param["bins"] = 768
+default_param["unstable_bins"] = 9  # training only
+default_param["reduction_bins"] = 762  # training only
+default_param["sr"] = 44100
+default_param["pre_filter_start"] = 757
+default_param["pre_filter_stop"] = 768
+default_param["band"] = {}
+
+
+default_param["band"][1] = {
+    "sr": 11025,
+    "hl": 128,
+    "n_fft": 960,
+    "crop_start": 0,
+    "crop_stop": 245,
+    "lpf_start": 61,  # inference only
+    "res_type": "polyphase",
+}
+
+default_param["band"][2] = {
+    "sr": 44100,
+    "hl": 512,
+    "n_fft": 1536,
+    "crop_start": 24,
+    "crop_stop": 547,
+    "hpf_start": 81,  # inference only
+    "res_type": "sinc_best",
+}
+
+
+def int_keys(d):
+    r = {}
+    for k, v in d:
+        if k.isdigit():
+            k = int(k)
+        r[k] = v
+    return r
+
+
+class ModelParameters(object):
+    def __init__(self, config_path=""):
+        if ".pth" == pathlib.Path(config_path).suffix:
+            import zipfile
+
+            with zipfile.ZipFile(config_path, "r") as zip:
+                self.param = json.loads(
+                    zip.read("param.json"), object_pairs_hook=int_keys
+                )
+        elif ".json" == pathlib.Path(config_path).suffix:
+            with open(config_path, "r") as f:
+                self.param = json.loads(f.read(), object_pairs_hook=int_keys)
+        else:
+            self.param = default_param
+
+        for k in [
+            "mid_side",
+            "mid_side_b",
+            "mid_side_b2",
+            "stereo_w",
+            "stereo_n",
+            "reverse",
+        ]:
+            if not k in self.param:
+                self.param[k] = False
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr16000_hl512.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr16000_hl512.json
new file mode 100644
index 0000000000000000000000000000000000000000..72cb4499867ad2827185e85687f06fb73d33eced
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr16000_hl512.json
@@ -0,0 +1,19 @@
+{
+	"bins": 1024,
+	"unstable_bins": 0,
+	"reduction_bins": 0,
+	"band": {
+		"1": {
+			"sr": 16000,
+			"hl": 512,
+			"n_fft": 2048,
+			"crop_start": 0,
+			"crop_stop": 1024,
+			"hpf_start": -1,
+			"res_type": "sinc_best"
+		}
+	},
+	"sr": 16000,
+	"pre_filter_start": 1023,
+	"pre_filter_stop": 1024
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c00ecf0a105e55a6a86a3c32db301a2635b5b41
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json
@@ -0,0 +1,19 @@
+{
+	"bins": 1024,
+	"unstable_bins": 0,
+	"reduction_bins": 0,
+	"band": {
+		"1": {
+			"sr": 32000,
+			"hl": 512,
+			"n_fft": 2048,
+			"crop_start": 0,
+			"crop_stop": 1024,
+			"hpf_start": -1,
+			"res_type": "kaiser_fast"
+		}
+	},
+	"sr": 32000,
+	"pre_filter_start": 1000,
+	"pre_filter_stop": 1021
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr33075_hl384.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr33075_hl384.json
new file mode 100644
index 0000000000000000000000000000000000000000..55666ac9a8d0547751fb4b4d3bffb1ee2c956913
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr33075_hl384.json
@@ -0,0 +1,19 @@
+{
+	"bins": 1024,
+	"unstable_bins": 0,
+	"reduction_bins": 0,
+	"band": {
+		"1": {
+			"sr": 33075,
+			"hl": 384,
+			"n_fft": 2048,
+			"crop_start": 0,
+			"crop_stop": 1024,
+			"hpf_start": -1,
+			"res_type": "sinc_best"
+		}
+	},
+	"sr": 33075,
+	"pre_filter_start": 1000,
+	"pre_filter_stop": 1021
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl1024.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl1024.json
new file mode 100644
index 0000000000000000000000000000000000000000..665abe20eb3cc39fe0f8493dad8f25f6ef634a14
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl1024.json
@@ -0,0 +1,19 @@
+{
+	"bins": 1024,
+	"unstable_bins": 0,
+	"reduction_bins": 0,
+	"band": {
+		"1": {
+			"sr": 44100,
+			"hl": 1024,
+			"n_fft": 2048,
+			"crop_start": 0,
+			"crop_stop": 1024,
+			"hpf_start": -1,
+			"res_type": "sinc_best"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 1023,
+	"pre_filter_stop": 1024
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl256.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl256.json
new file mode 100644
index 0000000000000000000000000000000000000000..0e8b16f89b0231d06eabe8d2f7c2670c7caa2272
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl256.json
@@ -0,0 +1,19 @@
+{
+	"bins": 256,
+	"unstable_bins": 0,
+	"reduction_bins": 0,
+	"band": {
+		"1": {
+			"sr": 44100,
+			"hl": 256,
+			"n_fft": 512,
+			"crop_start": 0,
+			"crop_stop": 256,
+			"hpf_start": -1,
+			"res_type": "sinc_best"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 256,
+	"pre_filter_stop": 256
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512.json
new file mode 100644
index 0000000000000000000000000000000000000000..3b38fcaf60ba204e03a47f5bd3f5bcfe75e1983a
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512.json
@@ -0,0 +1,19 @@
+{
+	"bins": 1024,
+	"unstable_bins": 0,
+	"reduction_bins": 0,
+	"band": {
+		"1": {
+			"sr": 44100,
+			"hl": 512,
+			"n_fft": 2048,
+			"crop_start": 0,
+			"crop_stop": 1024,
+			"hpf_start": -1,
+			"res_type": "sinc_best"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 1023,
+	"pre_filter_stop": 1024
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512_cut.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512_cut.json
new file mode 100644
index 0000000000000000000000000000000000000000..630df3524e340f43a1ddb7b33ff02cc91fc1cb47
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512_cut.json
@@ -0,0 +1,19 @@
+{
+	"bins": 1024,
+	"unstable_bins": 0,
+	"reduction_bins": 0,
+	"band": {
+		"1": {
+			"sr": 44100,
+			"hl": 512,
+			"n_fft": 2048,
+			"crop_start": 0,
+			"crop_stop": 700,
+			"hpf_start": -1,
+			"res_type": "sinc_best"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 1023,
+	"pre_filter_stop": 700
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/2band_32000.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/2band_32000.json
new file mode 100644
index 0000000000000000000000000000000000000000..ab9cf1150a818eb6252105408311be0a40d423b3
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/2band_32000.json
@@ -0,0 +1,30 @@
+{
+	"bins": 768,
+	"unstable_bins": 7,
+	"reduction_bins": 705,
+	"band": {
+		"1": {
+			"sr": 6000,
+			"hl": 66,
+			"n_fft": 512,
+			"crop_start": 0,
+			"crop_stop": 240,
+			"lpf_start": 60,
+			"lpf_stop": 118,
+			"res_type": "sinc_fastest"
+		},
+		"2": {
+			"sr": 32000,
+			"hl": 352,
+			"n_fft": 1024,
+			"crop_start": 22,
+			"crop_stop": 505,
+			"hpf_start": 44,
+			"hpf_stop": 23,
+			"res_type": "sinc_medium"
+		}
+	},
+	"sr": 32000,
+	"pre_filter_start": 710,
+	"pre_filter_stop": 731
+}
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/2band_44100_lofi.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/2band_44100_lofi.json
new file mode 100644
index 0000000000000000000000000000000000000000..7faa216d7b49aeece24123dbdd868847a1dbc03c
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/2band_44100_lofi.json
@@ -0,0 +1,30 @@
+{
+	"bins": 512,
+	"unstable_bins": 7,
+	"reduction_bins": 510,
+	"band": {
+		"1": {
+			"sr": 11025,
+			"hl": 160,
+			"n_fft": 768,
+			"crop_start": 0,
+			"crop_stop": 192,
+			"lpf_start": 41,
+			"lpf_stop": 139,
+			"res_type": "sinc_fastest"
+		},
+		"2": {
+			"sr": 44100,
+			"hl": 640,
+			"n_fft": 1024,
+			"crop_start": 10,
+			"crop_stop": 320,
+			"hpf_start": 47,
+			"hpf_stop": 15,
+			"res_type": "sinc_medium"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 510,
+	"pre_filter_stop": 512
+}
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/2band_48000.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/2band_48000.json
new file mode 100644
index 0000000000000000000000000000000000000000..7e78175052b09cb1a32345e54006475992712f9a
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/2band_48000.json
@@ -0,0 +1,30 @@
+{
+	"bins": 768,
+	"unstable_bins": 7,
+	"reduction_bins": 705,
+	"band": {
+		"1": {
+			"sr": 6000,
+			"hl": 66,
+			"n_fft": 512,
+			"crop_start": 0,
+			"crop_stop": 240,
+			"lpf_start": 60,
+			"lpf_stop": 240,
+			"res_type": "sinc_fastest"
+		},
+		"2": {
+			"sr": 48000,
+			"hl": 528,
+			"n_fft": 1536,
+			"crop_start": 22,
+			"crop_stop": 505,
+			"hpf_start": 82,
+			"hpf_stop": 22,
+			"res_type": "sinc_medium"
+		}
+	},
+	"sr": 48000,
+	"pre_filter_start": 710,
+	"pre_filter_stop": 731
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/3band_44100.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/3band_44100.json
new file mode 100644
index 0000000000000000000000000000000000000000..d881d767ff83fbac0e18dfe2587ef16925b29b3c
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/3band_44100.json
@@ -0,0 +1,42 @@
+{
+	"bins": 768,
+	"unstable_bins": 5,
+	"reduction_bins": 733,
+	"band": {
+		"1": {
+			"sr": 11025,
+			"hl": 128,
+			"n_fft": 768,
+			"crop_start": 0,
+			"crop_stop": 278,
+			"lpf_start": 28,
+			"lpf_stop": 140,
+			"res_type": "polyphase"
+		},
+		"2": {
+			"sr": 22050,
+			"hl": 256,
+			"n_fft": 768,
+			"crop_start": 14,
+			"crop_stop": 322,
+			"hpf_start": 70,
+			"hpf_stop": 14,
+			"lpf_start": 283,
+			"lpf_stop": 314,
+			"res_type": "polyphase"
+		},	
+		"3": {
+			"sr": 44100,
+			"hl": 512,
+			"n_fft": 768,
+			"crop_start": 131,
+			"crop_stop": 313,
+			"hpf_start": 154,
+			"hpf_stop": 141,
+			"res_type": "sinc_medium"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 757,
+	"pre_filter_stop": 768
+}
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/3band_44100_mid.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/3band_44100_mid.json
new file mode 100644
index 0000000000000000000000000000000000000000..77ec198573b19f36519a028a509767d30764c0e2
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/3band_44100_mid.json
@@ -0,0 +1,43 @@
+{
+	"mid_side": true,
+	"bins": 768,
+	"unstable_bins": 5,
+	"reduction_bins": 733,
+	"band": {
+		"1": {
+			"sr": 11025,
+			"hl": 128,
+			"n_fft": 768,
+			"crop_start": 0,
+			"crop_stop": 278,
+			"lpf_start": 28,
+			"lpf_stop": 140,
+			"res_type": "polyphase"
+		},
+		"2": {
+			"sr": 22050,
+			"hl": 256,
+			"n_fft": 768,
+			"crop_start": 14,
+			"crop_stop": 322,
+			"hpf_start": 70,
+			"hpf_stop": 14,
+			"lpf_start": 283,
+			"lpf_stop": 314,
+			"res_type": "polyphase"
+		},	
+		"3": {
+			"sr": 44100,
+			"hl": 512,
+			"n_fft": 768,
+			"crop_start": 131,
+			"crop_stop": 313,
+			"hpf_start": 154,
+			"hpf_stop": 141,
+			"res_type": "sinc_medium"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 757,
+	"pre_filter_stop": 768
+}
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/3band_44100_msb2.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/3band_44100_msb2.json
new file mode 100644
index 0000000000000000000000000000000000000000..85ee8a7d44541c9176e85ea3dce8728d34990938
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/3band_44100_msb2.json
@@ -0,0 +1,43 @@
+{
+	"mid_side_b2": true,
+	"bins": 640,
+	"unstable_bins": 7,
+	"reduction_bins": 565,
+	"band": {
+		"1": {
+			"sr": 11025,
+			"hl": 108,
+			"n_fft": 1024,
+			"crop_start": 0,
+			"crop_stop": 187,
+			"lpf_start": 92,
+			"lpf_stop": 186,
+			"res_type": "polyphase"
+		},
+		"2": {
+			"sr": 22050,
+			"hl": 216,
+			"n_fft": 768,
+			"crop_start": 0,
+			"crop_stop": 212,
+			"hpf_start": 68,
+			"hpf_stop": 34,
+			"lpf_start": 174,
+			"lpf_stop": 209,
+			"res_type": "polyphase"
+		},	
+		"3": {
+			"sr": 44100,
+			"hl": 432,
+			"n_fft": 640,
+			"crop_start": 66,
+			"crop_stop": 307,
+			"hpf_start": 86,
+			"hpf_stop": 72,
+			"res_type": "kaiser_fast"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 639,
+	"pre_filter_stop": 640
+}
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100.json
new file mode 100644
index 0000000000000000000000000000000000000000..df123754204372aa50d464fbe9102a401f48cc73
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100.json
@@ -0,0 +1,54 @@
+{
+	"bins": 768,
+	"unstable_bins": 7,
+	"reduction_bins": 668,
+	"band": {
+		"1": {
+			"sr": 11025,
+			"hl": 128,
+			"n_fft": 1024,
+			"crop_start": 0,
+			"crop_stop": 186,
+			"lpf_start": 37,
+			"lpf_stop": 73,
+			"res_type": "polyphase"
+		},
+		"2": {
+			"sr": 11025,
+			"hl": 128,
+			"n_fft": 512,
+			"crop_start": 4,
+			"crop_stop": 185,			
+			"hpf_start": 36,
+			"hpf_stop": 18,
+			"lpf_start": 93,
+			"lpf_stop": 185,
+			"res_type": "polyphase"
+		},
+		"3": {
+			"sr": 22050,
+			"hl": 256,
+			"n_fft": 512,
+			"crop_start": 46,
+			"crop_stop": 186,
+			"hpf_start": 93,
+			"hpf_stop": 46,
+			"lpf_start": 164,
+			"lpf_stop": 186,
+			"res_type": "polyphase"
+		},	
+		"4": {
+			"sr": 44100,
+			"hl": 512,
+			"n_fft": 768,
+			"crop_start": 121,
+			"crop_stop": 382,
+			"hpf_start": 138,
+			"hpf_stop": 123,
+			"res_type": "sinc_medium"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 740,
+	"pre_filter_stop": 768
+}
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100_mid.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100_mid.json
new file mode 100644
index 0000000000000000000000000000000000000000..e91b699eb63d3382c3b9e9edf46d40ed91d6122b
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100_mid.json
@@ -0,0 +1,55 @@
+{
+	"bins": 768,
+	"unstable_bins": 7,
+	"mid_side": true,
+	"reduction_bins": 668,
+	"band": {
+		"1": {
+			"sr": 11025,
+			"hl": 128,
+			"n_fft": 1024,
+			"crop_start": 0,
+			"crop_stop": 186,
+			"lpf_start": 37,
+			"lpf_stop": 73,
+			"res_type": "polyphase"
+		},
+		"2": {
+			"sr": 11025,
+			"hl": 128,
+			"n_fft": 512,
+			"crop_start": 4,
+			"crop_stop": 185,			
+			"hpf_start": 36,
+			"hpf_stop": 18,
+			"lpf_start": 93,
+			"lpf_stop": 185,
+			"res_type": "polyphase"
+		},
+		"3": {
+			"sr": 22050,
+			"hl": 256,
+			"n_fft": 512,
+			"crop_start": 46,
+			"crop_stop": 186,
+			"hpf_start": 93,
+			"hpf_stop": 46,
+			"lpf_start": 164,
+			"lpf_stop": 186,
+			"res_type": "polyphase"
+		},	
+		"4": {
+			"sr": 44100,
+			"hl": 512,
+			"n_fft": 768,
+			"crop_start": 121,
+			"crop_stop": 382,
+			"hpf_start": 138,
+			"hpf_stop": 123,
+			"res_type": "sinc_medium"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 740,
+	"pre_filter_stop": 768
+}
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100_msb.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100_msb.json
new file mode 100644
index 0000000000000000000000000000000000000000..f852f280ec9d98fc1b65cec688290eaafec61b84
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100_msb.json
@@ -0,0 +1,55 @@
+{
+	"mid_side_b": true,
+	"bins": 768,
+	"unstable_bins": 7,
+	"reduction_bins": 668,
+	"band": {
+		"1": {
+			"sr": 11025,
+			"hl": 128,
+			"n_fft": 1024,
+			"crop_start": 0,
+			"crop_stop": 186,
+			"lpf_start": 37,
+			"lpf_stop": 73,
+			"res_type": "polyphase"
+		},
+		"2": {
+			"sr": 11025,
+			"hl": 128,
+			"n_fft": 512,
+			"crop_start": 4,
+			"crop_stop": 185,			
+			"hpf_start": 36,
+			"hpf_stop": 18,
+			"lpf_start": 93,
+			"lpf_stop": 185,
+			"res_type": "polyphase"
+		},
+		"3": {
+			"sr": 22050,
+			"hl": 256,
+			"n_fft": 512,
+			"crop_start": 46,
+			"crop_stop": 186,
+			"hpf_start": 93,
+			"hpf_stop": 46,
+			"lpf_start": 164,
+			"lpf_stop": 186,
+			"res_type": "polyphase"
+		},	
+		"4": {
+			"sr": 44100,
+			"hl": 512,
+			"n_fft": 768,
+			"crop_start": 121,
+			"crop_stop": 382,
+			"hpf_start": 138,
+			"hpf_stop": 123,
+			"res_type": "sinc_medium"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 740,
+	"pre_filter_stop": 768
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100_msb2.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100_msb2.json
new file mode 100644
index 0000000000000000000000000000000000000000..f852f280ec9d98fc1b65cec688290eaafec61b84
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100_msb2.json
@@ -0,0 +1,55 @@
+{
+	"mid_side_b": true,
+	"bins": 768,
+	"unstable_bins": 7,
+	"reduction_bins": 668,
+	"band": {
+		"1": {
+			"sr": 11025,
+			"hl": 128,
+			"n_fft": 1024,
+			"crop_start": 0,
+			"crop_stop": 186,
+			"lpf_start": 37,
+			"lpf_stop": 73,
+			"res_type": "polyphase"
+		},
+		"2": {
+			"sr": 11025,
+			"hl": 128,
+			"n_fft": 512,
+			"crop_start": 4,
+			"crop_stop": 185,			
+			"hpf_start": 36,
+			"hpf_stop": 18,
+			"lpf_start": 93,
+			"lpf_stop": 185,
+			"res_type": "polyphase"
+		},
+		"3": {
+			"sr": 22050,
+			"hl": 256,
+			"n_fft": 512,
+			"crop_start": 46,
+			"crop_stop": 186,
+			"hpf_start": 93,
+			"hpf_stop": 46,
+			"lpf_start": 164,
+			"lpf_stop": 186,
+			"res_type": "polyphase"
+		},	
+		"4": {
+			"sr": 44100,
+			"hl": 512,
+			"n_fft": 768,
+			"crop_start": 121,
+			"crop_stop": 382,
+			"hpf_start": 138,
+			"hpf_stop": 123,
+			"res_type": "sinc_medium"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 740,
+	"pre_filter_stop": 768
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100_reverse.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100_reverse.json
new file mode 100644
index 0000000000000000000000000000000000000000..7a07d5541bd83dc1caa20b531c3b43a2ffccac88
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100_reverse.json
@@ -0,0 +1,55 @@
+{
+	"reverse": true,
+	"bins": 768,
+	"unstable_bins": 7,
+	"reduction_bins": 668,
+	"band": {
+		"1": {
+			"sr": 11025,
+			"hl": 128,
+			"n_fft": 1024,
+			"crop_start": 0,
+			"crop_stop": 186,
+			"lpf_start": 37,
+			"lpf_stop": 73,
+			"res_type": "polyphase"
+		},
+		"2": {
+			"sr": 11025,
+			"hl": 128,
+			"n_fft": 512,
+			"crop_start": 4,
+			"crop_stop": 185,			
+			"hpf_start": 36,
+			"hpf_stop": 18,
+			"lpf_start": 93,
+			"lpf_stop": 185,
+			"res_type": "polyphase"
+		},
+		"3": {
+			"sr": 22050,
+			"hl": 256,
+			"n_fft": 512,
+			"crop_start": 46,
+			"crop_stop": 186,
+			"hpf_start": 93,
+			"hpf_stop": 46,
+			"lpf_start": 164,
+			"lpf_stop": 186,
+			"res_type": "polyphase"
+		},	
+		"4": {
+			"sr": 44100,
+			"hl": 512,
+			"n_fft": 768,
+			"crop_start": 121,
+			"crop_stop": 382,
+			"hpf_start": 138,
+			"hpf_stop": 123,
+			"res_type": "sinc_medium"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 740,
+	"pre_filter_stop": 768
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100_sw.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100_sw.json
new file mode 100644
index 0000000000000000000000000000000000000000..ba0cf342106de793e6ec3e876854c7fd451fbf76
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_44100_sw.json
@@ -0,0 +1,55 @@
+{
+	"stereo_w": true,
+	"bins": 768,
+	"unstable_bins": 7,
+	"reduction_bins": 668,
+	"band": {
+		"1": {
+			"sr": 11025,
+			"hl": 128,
+			"n_fft": 1024,
+			"crop_start": 0,
+			"crop_stop": 186,
+			"lpf_start": 37,
+			"lpf_stop": 73,
+			"res_type": "polyphase"
+		},
+		"2": {
+			"sr": 11025,
+			"hl": 128,
+			"n_fft": 512,
+			"crop_start": 4,
+			"crop_stop": 185,			
+			"hpf_start": 36,
+			"hpf_stop": 18,
+			"lpf_start": 93,
+			"lpf_stop": 185,
+			"res_type": "polyphase"
+		},
+		"3": {
+			"sr": 22050,
+			"hl": 256,
+			"n_fft": 512,
+			"crop_start": 46,
+			"crop_stop": 186,
+			"hpf_start": 93,
+			"hpf_stop": 46,
+			"lpf_start": 164,
+			"lpf_stop": 186,
+			"res_type": "polyphase"
+		},	
+		"4": {
+			"sr": 44100,
+			"hl": 512,
+			"n_fft": 768,
+			"crop_start": 121,
+			"crop_stop": 382,
+			"hpf_start": 138,
+			"hpf_stop": 123,
+			"res_type": "sinc_medium"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 740,
+	"pre_filter_stop": 768
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_v2.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_v2.json
new file mode 100644
index 0000000000000000000000000000000000000000..33281a0cf9916fc33558ddfda7a0287a2547faf4
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_v2.json
@@ -0,0 +1,54 @@
+{
+	"bins": 672,
+	"unstable_bins": 8,
+	"reduction_bins": 637,
+	"band": {
+		"1": {
+			"sr": 7350,
+			"hl": 80,
+			"n_fft": 640,
+			"crop_start": 0,
+			"crop_stop": 85,
+			"lpf_start": 25,
+			"lpf_stop": 53,
+			"res_type": "polyphase"
+		},
+		"2": {
+			"sr": 7350,
+			"hl": 80,
+			"n_fft": 320,
+			"crop_start": 4,
+			"crop_stop": 87,
+			"hpf_start": 25,
+			"hpf_stop": 12,
+			"lpf_start": 31,
+			"lpf_stop": 62,
+			"res_type": "polyphase"
+		},		
+		"3": {
+			"sr": 14700,
+			"hl": 160,
+			"n_fft": 512,
+			"crop_start": 17,
+			"crop_stop": 216,
+			"hpf_start": 48,
+			"hpf_stop": 24,
+			"lpf_start": 139,
+			"lpf_stop": 210,
+			"res_type": "polyphase"
+		},	
+		"4": {
+			"sr": 44100,
+			"hl": 480,
+			"n_fft": 960,
+			"crop_start": 78,
+			"crop_stop": 383,
+			"hpf_start": 130,
+			"hpf_stop": 86,
+			"res_type": "kaiser_fast"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 668,
+	"pre_filter_stop": 672
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_v2_sn.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_v2_sn.json
new file mode 100644
index 0000000000000000000000000000000000000000..2e5c770fe188779bf6b0873190b7a324d6a867b2
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_v2_sn.json
@@ -0,0 +1,55 @@
+{
+	"bins": 672,
+	"unstable_bins": 8,
+	"reduction_bins": 637,
+	"band": {
+		"1": {
+			"sr": 7350,
+			"hl": 80,
+			"n_fft": 640,
+			"crop_start": 0,
+			"crop_stop": 85,
+			"lpf_start": 25,
+			"lpf_stop": 53,
+			"res_type": "polyphase"
+		},
+		"2": {
+			"sr": 7350,
+			"hl": 80,
+			"n_fft": 320,
+			"crop_start": 4,
+			"crop_stop": 87,
+			"hpf_start": 25,
+			"hpf_stop": 12,
+			"lpf_start": 31,
+			"lpf_stop": 62,
+			"res_type": "polyphase"
+		},		
+		"3": {
+			"sr": 14700,
+			"hl": 160,
+			"n_fft": 512,
+			"crop_start": 17,
+			"crop_stop": 216,
+			"hpf_start": 48,
+			"hpf_stop": 24,
+			"lpf_start": 139,
+			"lpf_stop": 210,
+			"res_type": "polyphase"
+		},	
+		"4": {
+			"sr": 44100,
+			"hl": 480,
+			"n_fft": 960,
+			"crop_start": 78,
+			"crop_stop": 383,
+			"hpf_start": 130,
+			"hpf_stop": 86,
+			"convert_channels": "stereo_n",
+			"res_type": "kaiser_fast"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 668,
+	"pre_filter_stop": 672
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_v3.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_v3.json
new file mode 100644
index 0000000000000000000000000000000000000000..2a73bc97ac545145a75bdca7addc5d59f5b8574b
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/4band_v3.json
@@ -0,0 +1,54 @@
+{
+	"bins": 672,
+	"unstable_bins": 8,
+	"reduction_bins": 530,
+	"band": {
+		"1": {
+			"sr": 7350,
+			"hl": 80,
+			"n_fft": 640,
+			"crop_start": 0,
+			"crop_stop": 85,
+			"lpf_start": 25,
+			"lpf_stop": 53,
+			"res_type": "polyphase"
+		},
+		"2": {
+			"sr": 7350,
+			"hl": 80,
+			"n_fft": 320,
+			"crop_start": 4,
+			"crop_stop": 87,
+			"hpf_start": 25,
+			"hpf_stop": 12,
+			"lpf_start": 31,
+			"lpf_stop": 62,
+			"res_type": "polyphase"
+		},
+		"3": {
+			"sr": 14700,
+			"hl": 160,
+			"n_fft": 512,
+			"crop_start": 17,
+			"crop_stop": 216,
+			"hpf_start": 48,
+			"hpf_stop": 24,
+			"lpf_start": 139,
+			"lpf_stop": 210,
+			"res_type": "polyphase"
+		},
+		"4": {
+			"sr": 44100,
+			"hl": 480,
+			"n_fft": 960,
+			"crop_start": 78,
+			"crop_stop": 383,
+			"hpf_start": 130,
+			"hpf_stop": 86,
+			"res_type": "kaiser_fast"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 668,
+	"pre_filter_stop": 672
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/modelparams/ensemble.json b/rvc/lib/uvr5_pack/lib_v5/modelparams/ensemble.json
new file mode 100644
index 0000000000000000000000000000000000000000..ee69beb46fc82f34619c5e48761e329fcabbbd00
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/modelparams/ensemble.json
@@ -0,0 +1,43 @@
+{
+	"mid_side_b2": true,
+	"bins": 1280,
+	"unstable_bins": 7,
+	"reduction_bins": 565,
+	"band": {
+		"1": {
+			"sr": 11025,
+			"hl": 108,
+			"n_fft": 2048,
+			"crop_start": 0,
+			"crop_stop": 374,
+			"lpf_start": 92,
+			"lpf_stop": 186,
+			"res_type": "polyphase"
+		},
+		"2": {
+			"sr": 22050,
+			"hl": 216,
+			"n_fft": 1536,
+			"crop_start": 0,
+			"crop_stop": 424,
+			"hpf_start": 68,
+			"hpf_stop": 34,
+			"lpf_start": 348,
+			"lpf_stop": 418,
+			"res_type": "polyphase"
+		},	
+		"3": {
+			"sr": 44100,
+			"hl": 432,
+			"n_fft": 1280,
+			"crop_start": 132,
+			"crop_stop": 614,
+			"hpf_start": 172,
+			"hpf_stop": 144,
+			"res_type": "polyphase"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 1280,
+	"pre_filter_stop": 1280
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/lib_v5/nets.py b/rvc/lib/uvr5_pack/lib_v5/nets.py
new file mode 100644
index 0000000000000000000000000000000000000000..5da3948c2f2e9edcc3cdac49bdf9f738e403de40
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/nets.py
@@ -0,0 +1,123 @@
+import layers
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from . import spec_utils
+
+
+class BaseASPPNet(nn.Module):
+    def __init__(self, nin, ch, dilations=(4, 8, 16)):
+        super(BaseASPPNet, self).__init__()
+        self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
+        self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
+        self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
+        self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
+
+        self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
+
+        self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
+        self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
+        self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
+        self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
+
+    def __call__(self, x):
+        h, e1 = self.enc1(x)
+        h, e2 = self.enc2(h)
+        h, e3 = self.enc3(h)
+        h, e4 = self.enc4(h)
+
+        h = self.aspp(h)
+
+        h = self.dec4(h, e4)
+        h = self.dec3(h, e3)
+        h = self.dec2(h, e2)
+        h = self.dec1(h, e1)
+
+        return h
+
+
+class CascadedASPPNet(nn.Module):
+    def __init__(self, n_fft):
+        super(CascadedASPPNet, self).__init__()
+        self.stg1_low_band_net = BaseASPPNet(2, 16)
+        self.stg1_high_band_net = BaseASPPNet(2, 16)
+
+        self.stg2_bridge = layers.Conv2DBNActiv(18, 8, 1, 1, 0)
+        self.stg2_full_band_net = BaseASPPNet(8, 16)
+
+        self.stg3_bridge = layers.Conv2DBNActiv(34, 16, 1, 1, 0)
+        self.stg3_full_band_net = BaseASPPNet(16, 32)
+
+        self.out = nn.Conv2d(32, 2, 1, bias=False)
+        self.aux1_out = nn.Conv2d(16, 2, 1, bias=False)
+        self.aux2_out = nn.Conv2d(16, 2, 1, bias=False)
+
+        self.max_bin = n_fft // 2
+        self.output_bin = n_fft // 2 + 1
+
+        self.offset = 128
+
+    def forward(self, x, aggressiveness=None):
+        mix = x.detach()
+        x = x.clone()
+
+        x = x[:, :, : self.max_bin]
+
+        bandw = x.size()[2] // 2
+        aux1 = torch.cat(
+            [
+                self.stg1_low_band_net(x[:, :, :bandw]),
+                self.stg1_high_band_net(x[:, :, bandw:]),
+            ],
+            dim=2,
+        )
+
+        h = torch.cat([x, aux1], dim=1)
+        aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
+
+        h = torch.cat([x, aux1, aux2], dim=1)
+        h = self.stg3_full_band_net(self.stg3_bridge(h))
+
+        mask = torch.sigmoid(self.out(h))
+        mask = F.pad(
+            input=mask,
+            pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+            mode="replicate",
+        )
+
+        if self.training:
+            aux1 = torch.sigmoid(self.aux1_out(aux1))
+            aux1 = F.pad(
+                input=aux1,
+                pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
+                mode="replicate",
+            )
+            aux2 = torch.sigmoid(self.aux2_out(aux2))
+            aux2 = F.pad(
+                input=aux2,
+                pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
+                mode="replicate",
+            )
+            return mask * mix, aux1 * mix, aux2 * mix
+        else:
+            if aggressiveness:
+                mask[:, :, : aggressiveness["split_bin"]] = torch.pow(
+                    mask[:, :, : aggressiveness["split_bin"]],
+                    1 + aggressiveness["value"] / 3,
+                )
+                mask[:, :, aggressiveness["split_bin"] :] = torch.pow(
+                    mask[:, :, aggressiveness["split_bin"] :],
+                    1 + aggressiveness["value"],
+                )
+
+            return mask * mix
+
+    def predict(self, x_mag, aggressiveness=None):
+        h = self.forward(x_mag, aggressiveness)
+
+        if self.offset > 0:
+            h = h[:, :, :, self.offset : -self.offset]
+            assert h.size()[3] > 0
+
+        return h
diff --git a/rvc/lib/uvr5_pack/lib_v5/nets_123812KB.py b/rvc/lib/uvr5_pack/lib_v5/nets_123812KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..167d4cb2198863cf43e93440f7e63c5342fc7605
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/nets_123812KB.py
@@ -0,0 +1,122 @@
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from . import layers_123821KB as layers
+
+
+class BaseASPPNet(nn.Module):
+    def __init__(self, nin, ch, dilations=(4, 8, 16)):
+        super(BaseASPPNet, self).__init__()
+        self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
+        self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
+        self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
+        self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
+
+        self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
+
+        self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
+        self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
+        self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
+        self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
+
+    def __call__(self, x):
+        h, e1 = self.enc1(x)
+        h, e2 = self.enc2(h)
+        h, e3 = self.enc3(h)
+        h, e4 = self.enc4(h)
+
+        h = self.aspp(h)
+
+        h = self.dec4(h, e4)
+        h = self.dec3(h, e3)
+        h = self.dec2(h, e2)
+        h = self.dec1(h, e1)
+
+        return h
+
+
+class CascadedASPPNet(nn.Module):
+    def __init__(self, n_fft):
+        super(CascadedASPPNet, self).__init__()
+        self.stg1_low_band_net = BaseASPPNet(2, 32)
+        self.stg1_high_band_net = BaseASPPNet(2, 32)
+
+        self.stg2_bridge = layers.Conv2DBNActiv(34, 16, 1, 1, 0)
+        self.stg2_full_band_net = BaseASPPNet(16, 32)
+
+        self.stg3_bridge = layers.Conv2DBNActiv(66, 32, 1, 1, 0)
+        self.stg3_full_band_net = BaseASPPNet(32, 64)
+
+        self.out = nn.Conv2d(64, 2, 1, bias=False)
+        self.aux1_out = nn.Conv2d(32, 2, 1, bias=False)
+        self.aux2_out = nn.Conv2d(32, 2, 1, bias=False)
+
+        self.max_bin = n_fft // 2
+        self.output_bin = n_fft // 2 + 1
+
+        self.offset = 128
+
+    def forward(self, x, aggressiveness=None):
+        mix = x.detach()
+        x = x.clone()
+
+        x = x[:, :, : self.max_bin]
+
+        bandw = x.size()[2] // 2
+        aux1 = torch.cat(
+            [
+                self.stg1_low_band_net(x[:, :, :bandw]),
+                self.stg1_high_band_net(x[:, :, bandw:]),
+            ],
+            dim=2,
+        )
+
+        h = torch.cat([x, aux1], dim=1)
+        aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
+
+        h = torch.cat([x, aux1, aux2], dim=1)
+        h = self.stg3_full_band_net(self.stg3_bridge(h))
+
+        mask = torch.sigmoid(self.out(h))
+        mask = F.pad(
+            input=mask,
+            pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+            mode="replicate",
+        )
+
+        if self.training:
+            aux1 = torch.sigmoid(self.aux1_out(aux1))
+            aux1 = F.pad(
+                input=aux1,
+                pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
+                mode="replicate",
+            )
+            aux2 = torch.sigmoid(self.aux2_out(aux2))
+            aux2 = F.pad(
+                input=aux2,
+                pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
+                mode="replicate",
+            )
+            return mask * mix, aux1 * mix, aux2 * mix
+        else:
+            if aggressiveness:
+                mask[:, :, : aggressiveness["split_bin"]] = torch.pow(
+                    mask[:, :, : aggressiveness["split_bin"]],
+                    1 + aggressiveness["value"] / 3,
+                )
+                mask[:, :, aggressiveness["split_bin"] :] = torch.pow(
+                    mask[:, :, aggressiveness["split_bin"] :],
+                    1 + aggressiveness["value"],
+                )
+
+            return mask * mix
+
+    def predict(self, x_mag, aggressiveness=None):
+        h = self.forward(x_mag, aggressiveness)
+
+        if self.offset > 0:
+            h = h[:, :, :, self.offset : -self.offset]
+            assert h.size()[3] > 0
+
+        return h
diff --git a/rvc/lib/uvr5_pack/lib_v5/nets_123821KB.py b/rvc/lib/uvr5_pack/lib_v5/nets_123821KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..167d4cb2198863cf43e93440f7e63c5342fc7605
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/nets_123821KB.py
@@ -0,0 +1,122 @@
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from . import layers_123821KB as layers
+
+
+class BaseASPPNet(nn.Module):
+    def __init__(self, nin, ch, dilations=(4, 8, 16)):
+        super(BaseASPPNet, self).__init__()
+        self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
+        self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
+        self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
+        self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
+
+        self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
+
+        self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
+        self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
+        self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
+        self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
+
+    def __call__(self, x):
+        h, e1 = self.enc1(x)
+        h, e2 = self.enc2(h)
+        h, e3 = self.enc3(h)
+        h, e4 = self.enc4(h)
+
+        h = self.aspp(h)
+
+        h = self.dec4(h, e4)
+        h = self.dec3(h, e3)
+        h = self.dec2(h, e2)
+        h = self.dec1(h, e1)
+
+        return h
+
+
+class CascadedASPPNet(nn.Module):
+    def __init__(self, n_fft):
+        super(CascadedASPPNet, self).__init__()
+        self.stg1_low_band_net = BaseASPPNet(2, 32)
+        self.stg1_high_band_net = BaseASPPNet(2, 32)
+
+        self.stg2_bridge = layers.Conv2DBNActiv(34, 16, 1, 1, 0)
+        self.stg2_full_band_net = BaseASPPNet(16, 32)
+
+        self.stg3_bridge = layers.Conv2DBNActiv(66, 32, 1, 1, 0)
+        self.stg3_full_band_net = BaseASPPNet(32, 64)
+
+        self.out = nn.Conv2d(64, 2, 1, bias=False)
+        self.aux1_out = nn.Conv2d(32, 2, 1, bias=False)
+        self.aux2_out = nn.Conv2d(32, 2, 1, bias=False)
+
+        self.max_bin = n_fft // 2
+        self.output_bin = n_fft // 2 + 1
+
+        self.offset = 128
+
+    def forward(self, x, aggressiveness=None):
+        mix = x.detach()
+        x = x.clone()
+
+        x = x[:, :, : self.max_bin]
+
+        bandw = x.size()[2] // 2
+        aux1 = torch.cat(
+            [
+                self.stg1_low_band_net(x[:, :, :bandw]),
+                self.stg1_high_band_net(x[:, :, bandw:]),
+            ],
+            dim=2,
+        )
+
+        h = torch.cat([x, aux1], dim=1)
+        aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
+
+        h = torch.cat([x, aux1, aux2], dim=1)
+        h = self.stg3_full_band_net(self.stg3_bridge(h))
+
+        mask = torch.sigmoid(self.out(h))
+        mask = F.pad(
+            input=mask,
+            pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+            mode="replicate",
+        )
+
+        if self.training:
+            aux1 = torch.sigmoid(self.aux1_out(aux1))
+            aux1 = F.pad(
+                input=aux1,
+                pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
+                mode="replicate",
+            )
+            aux2 = torch.sigmoid(self.aux2_out(aux2))
+            aux2 = F.pad(
+                input=aux2,
+                pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
+                mode="replicate",
+            )
+            return mask * mix, aux1 * mix, aux2 * mix
+        else:
+            if aggressiveness:
+                mask[:, :, : aggressiveness["split_bin"]] = torch.pow(
+                    mask[:, :, : aggressiveness["split_bin"]],
+                    1 + aggressiveness["value"] / 3,
+                )
+                mask[:, :, aggressiveness["split_bin"] :] = torch.pow(
+                    mask[:, :, aggressiveness["split_bin"] :],
+                    1 + aggressiveness["value"],
+                )
+
+            return mask * mix
+
+    def predict(self, x_mag, aggressiveness=None):
+        h = self.forward(x_mag, aggressiveness)
+
+        if self.offset > 0:
+            h = h[:, :, :, self.offset : -self.offset]
+            assert h.size()[3] > 0
+
+        return h
diff --git a/rvc/lib/uvr5_pack/lib_v5/nets_33966KB.py b/rvc/lib/uvr5_pack/lib_v5/nets_33966KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..73a5b836177b706c306e27875f8391c1aed4b948
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/nets_33966KB.py
@@ -0,0 +1,122 @@
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from . import layers_33966KB as layers
+
+
+class BaseASPPNet(nn.Module):
+    def __init__(self, nin, ch, dilations=(4, 8, 16, 32)):
+        super(BaseASPPNet, self).__init__()
+        self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
+        self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
+        self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
+        self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
+
+        self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
+
+        self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
+        self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
+        self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
+        self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
+
+    def __call__(self, x):
+        h, e1 = self.enc1(x)
+        h, e2 = self.enc2(h)
+        h, e3 = self.enc3(h)
+        h, e4 = self.enc4(h)
+
+        h = self.aspp(h)
+
+        h = self.dec4(h, e4)
+        h = self.dec3(h, e3)
+        h = self.dec2(h, e2)
+        h = self.dec1(h, e1)
+
+        return h
+
+
+class CascadedASPPNet(nn.Module):
+    def __init__(self, n_fft):
+        super(CascadedASPPNet, self).__init__()
+        self.stg1_low_band_net = BaseASPPNet(2, 16)
+        self.stg1_high_band_net = BaseASPPNet(2, 16)
+
+        self.stg2_bridge = layers.Conv2DBNActiv(18, 8, 1, 1, 0)
+        self.stg2_full_band_net = BaseASPPNet(8, 16)
+
+        self.stg3_bridge = layers.Conv2DBNActiv(34, 16, 1, 1, 0)
+        self.stg3_full_band_net = BaseASPPNet(16, 32)
+
+        self.out = nn.Conv2d(32, 2, 1, bias=False)
+        self.aux1_out = nn.Conv2d(16, 2, 1, bias=False)
+        self.aux2_out = nn.Conv2d(16, 2, 1, bias=False)
+
+        self.max_bin = n_fft // 2
+        self.output_bin = n_fft // 2 + 1
+
+        self.offset = 128
+
+    def forward(self, x, aggressiveness=None):
+        mix = x.detach()
+        x = x.clone()
+
+        x = x[:, :, : self.max_bin]
+
+        bandw = x.size()[2] // 2
+        aux1 = torch.cat(
+            [
+                self.stg1_low_band_net(x[:, :, :bandw]),
+                self.stg1_high_band_net(x[:, :, bandw:]),
+            ],
+            dim=2,
+        )
+
+        h = torch.cat([x, aux1], dim=1)
+        aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
+
+        h = torch.cat([x, aux1, aux2], dim=1)
+        h = self.stg3_full_band_net(self.stg3_bridge(h))
+
+        mask = torch.sigmoid(self.out(h))
+        mask = F.pad(
+            input=mask,
+            pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+            mode="replicate",
+        )
+
+        if self.training:
+            aux1 = torch.sigmoid(self.aux1_out(aux1))
+            aux1 = F.pad(
+                input=aux1,
+                pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
+                mode="replicate",
+            )
+            aux2 = torch.sigmoid(self.aux2_out(aux2))
+            aux2 = F.pad(
+                input=aux2,
+                pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
+                mode="replicate",
+            )
+            return mask * mix, aux1 * mix, aux2 * mix
+        else:
+            if aggressiveness:
+                mask[:, :, : aggressiveness["split_bin"]] = torch.pow(
+                    mask[:, :, : aggressiveness["split_bin"]],
+                    1 + aggressiveness["value"] / 3,
+                )
+                mask[:, :, aggressiveness["split_bin"] :] = torch.pow(
+                    mask[:, :, aggressiveness["split_bin"] :],
+                    1 + aggressiveness["value"],
+                )
+
+            return mask * mix
+
+    def predict(self, x_mag, aggressiveness=None):
+        h = self.forward(x_mag, aggressiveness)
+
+        if self.offset > 0:
+            h = h[:, :, :, self.offset : -self.offset]
+            assert h.size()[3] > 0
+
+        return h
diff --git a/rvc/lib/uvr5_pack/lib_v5/nets_537227KB.py b/rvc/lib/uvr5_pack/lib_v5/nets_537227KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..823b44fb64898e8dcbb12180ba45d1718f9b03f7
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/nets_537227KB.py
@@ -0,0 +1,123 @@
+import numpy as np
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from . import layers_537238KB as layers
+
+
+class BaseASPPNet(nn.Module):
+    def __init__(self, nin, ch, dilations=(4, 8, 16)):
+        super(BaseASPPNet, self).__init__()
+        self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
+        self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
+        self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
+        self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
+
+        self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
+
+        self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
+        self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
+        self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
+        self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
+
+    def __call__(self, x):
+        h, e1 = self.enc1(x)
+        h, e2 = self.enc2(h)
+        h, e3 = self.enc3(h)
+        h, e4 = self.enc4(h)
+
+        h = self.aspp(h)
+
+        h = self.dec4(h, e4)
+        h = self.dec3(h, e3)
+        h = self.dec2(h, e2)
+        h = self.dec1(h, e1)
+
+        return h
+
+
+class CascadedASPPNet(nn.Module):
+    def __init__(self, n_fft):
+        super(CascadedASPPNet, self).__init__()
+        self.stg1_low_band_net = BaseASPPNet(2, 64)
+        self.stg1_high_band_net = BaseASPPNet(2, 64)
+
+        self.stg2_bridge = layers.Conv2DBNActiv(66, 32, 1, 1, 0)
+        self.stg2_full_band_net = BaseASPPNet(32, 64)
+
+        self.stg3_bridge = layers.Conv2DBNActiv(130, 64, 1, 1, 0)
+        self.stg3_full_band_net = BaseASPPNet(64, 128)
+
+        self.out = nn.Conv2d(128, 2, 1, bias=False)
+        self.aux1_out = nn.Conv2d(64, 2, 1, bias=False)
+        self.aux2_out = nn.Conv2d(64, 2, 1, bias=False)
+
+        self.max_bin = n_fft // 2
+        self.output_bin = n_fft // 2 + 1
+
+        self.offset = 128
+
+    def forward(self, x, aggressiveness=None):
+        mix = x.detach()
+        x = x.clone()
+
+        x = x[:, :, : self.max_bin]
+
+        bandw = x.size()[2] // 2
+        aux1 = torch.cat(
+            [
+                self.stg1_low_band_net(x[:, :, :bandw]),
+                self.stg1_high_band_net(x[:, :, bandw:]),
+            ],
+            dim=2,
+        )
+
+        h = torch.cat([x, aux1], dim=1)
+        aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
+
+        h = torch.cat([x, aux1, aux2], dim=1)
+        h = self.stg3_full_band_net(self.stg3_bridge(h))
+
+        mask = torch.sigmoid(self.out(h))
+        mask = F.pad(
+            input=mask,
+            pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+            mode="replicate",
+        )
+
+        if self.training:
+            aux1 = torch.sigmoid(self.aux1_out(aux1))
+            aux1 = F.pad(
+                input=aux1,
+                pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
+                mode="replicate",
+            )
+            aux2 = torch.sigmoid(self.aux2_out(aux2))
+            aux2 = F.pad(
+                input=aux2,
+                pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
+                mode="replicate",
+            )
+            return mask * mix, aux1 * mix, aux2 * mix
+        else:
+            if aggressiveness:
+                mask[:, :, : aggressiveness["split_bin"]] = torch.pow(
+                    mask[:, :, : aggressiveness["split_bin"]],
+                    1 + aggressiveness["value"] / 3,
+                )
+                mask[:, :, aggressiveness["split_bin"] :] = torch.pow(
+                    mask[:, :, aggressiveness["split_bin"] :],
+                    1 + aggressiveness["value"],
+                )
+
+            return mask * mix
+
+    def predict(self, x_mag, aggressiveness=None):
+        h = self.forward(x_mag, aggressiveness)
+
+        if self.offset > 0:
+            h = h[:, :, :, self.offset : -self.offset]
+            assert h.size()[3] > 0
+
+        return h
diff --git a/rvc/lib/uvr5_pack/lib_v5/nets_537238KB.py b/rvc/lib/uvr5_pack/lib_v5/nets_537238KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..823b44fb64898e8dcbb12180ba45d1718f9b03f7
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/nets_537238KB.py
@@ -0,0 +1,123 @@
+import numpy as np
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from . import layers_537238KB as layers
+
+
+class BaseASPPNet(nn.Module):
+    def __init__(self, nin, ch, dilations=(4, 8, 16)):
+        super(BaseASPPNet, self).__init__()
+        self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
+        self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
+        self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
+        self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
+
+        self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
+
+        self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
+        self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
+        self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
+        self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
+
+    def __call__(self, x):
+        h, e1 = self.enc1(x)
+        h, e2 = self.enc2(h)
+        h, e3 = self.enc3(h)
+        h, e4 = self.enc4(h)
+
+        h = self.aspp(h)
+
+        h = self.dec4(h, e4)
+        h = self.dec3(h, e3)
+        h = self.dec2(h, e2)
+        h = self.dec1(h, e1)
+
+        return h
+
+
+class CascadedASPPNet(nn.Module):
+    def __init__(self, n_fft):
+        super(CascadedASPPNet, self).__init__()
+        self.stg1_low_band_net = BaseASPPNet(2, 64)
+        self.stg1_high_band_net = BaseASPPNet(2, 64)
+
+        self.stg2_bridge = layers.Conv2DBNActiv(66, 32, 1, 1, 0)
+        self.stg2_full_band_net = BaseASPPNet(32, 64)
+
+        self.stg3_bridge = layers.Conv2DBNActiv(130, 64, 1, 1, 0)
+        self.stg3_full_band_net = BaseASPPNet(64, 128)
+
+        self.out = nn.Conv2d(128, 2, 1, bias=False)
+        self.aux1_out = nn.Conv2d(64, 2, 1, bias=False)
+        self.aux2_out = nn.Conv2d(64, 2, 1, bias=False)
+
+        self.max_bin = n_fft // 2
+        self.output_bin = n_fft // 2 + 1
+
+        self.offset = 128
+
+    def forward(self, x, aggressiveness=None):
+        mix = x.detach()
+        x = x.clone()
+
+        x = x[:, :, : self.max_bin]
+
+        bandw = x.size()[2] // 2
+        aux1 = torch.cat(
+            [
+                self.stg1_low_band_net(x[:, :, :bandw]),
+                self.stg1_high_band_net(x[:, :, bandw:]),
+            ],
+            dim=2,
+        )
+
+        h = torch.cat([x, aux1], dim=1)
+        aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
+
+        h = torch.cat([x, aux1, aux2], dim=1)
+        h = self.stg3_full_band_net(self.stg3_bridge(h))
+
+        mask = torch.sigmoid(self.out(h))
+        mask = F.pad(
+            input=mask,
+            pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+            mode="replicate",
+        )
+
+        if self.training:
+            aux1 = torch.sigmoid(self.aux1_out(aux1))
+            aux1 = F.pad(
+                input=aux1,
+                pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
+                mode="replicate",
+            )
+            aux2 = torch.sigmoid(self.aux2_out(aux2))
+            aux2 = F.pad(
+                input=aux2,
+                pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
+                mode="replicate",
+            )
+            return mask * mix, aux1 * mix, aux2 * mix
+        else:
+            if aggressiveness:
+                mask[:, :, : aggressiveness["split_bin"]] = torch.pow(
+                    mask[:, :, : aggressiveness["split_bin"]],
+                    1 + aggressiveness["value"] / 3,
+                )
+                mask[:, :, aggressiveness["split_bin"] :] = torch.pow(
+                    mask[:, :, aggressiveness["split_bin"] :],
+                    1 + aggressiveness["value"],
+                )
+
+            return mask * mix
+
+    def predict(self, x_mag, aggressiveness=None):
+        h = self.forward(x_mag, aggressiveness)
+
+        if self.offset > 0:
+            h = h[:, :, :, self.offset : -self.offset]
+            assert h.size()[3] > 0
+
+        return h
diff --git a/rvc/lib/uvr5_pack/lib_v5/nets_61968KB.py b/rvc/lib/uvr5_pack/lib_v5/nets_61968KB.py
new file mode 100644
index 0000000000000000000000000000000000000000..167d4cb2198863cf43e93440f7e63c5342fc7605
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/nets_61968KB.py
@@ -0,0 +1,122 @@
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from . import layers_123821KB as layers
+
+
+class BaseASPPNet(nn.Module):
+    def __init__(self, nin, ch, dilations=(4, 8, 16)):
+        super(BaseASPPNet, self).__init__()
+        self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
+        self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
+        self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
+        self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
+
+        self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
+
+        self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
+        self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
+        self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
+        self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
+
+    def __call__(self, x):
+        h, e1 = self.enc1(x)
+        h, e2 = self.enc2(h)
+        h, e3 = self.enc3(h)
+        h, e4 = self.enc4(h)
+
+        h = self.aspp(h)
+
+        h = self.dec4(h, e4)
+        h = self.dec3(h, e3)
+        h = self.dec2(h, e2)
+        h = self.dec1(h, e1)
+
+        return h
+
+
+class CascadedASPPNet(nn.Module):
+    def __init__(self, n_fft):
+        super(CascadedASPPNet, self).__init__()
+        self.stg1_low_band_net = BaseASPPNet(2, 32)
+        self.stg1_high_band_net = BaseASPPNet(2, 32)
+
+        self.stg2_bridge = layers.Conv2DBNActiv(34, 16, 1, 1, 0)
+        self.stg2_full_band_net = BaseASPPNet(16, 32)
+
+        self.stg3_bridge = layers.Conv2DBNActiv(66, 32, 1, 1, 0)
+        self.stg3_full_band_net = BaseASPPNet(32, 64)
+
+        self.out = nn.Conv2d(64, 2, 1, bias=False)
+        self.aux1_out = nn.Conv2d(32, 2, 1, bias=False)
+        self.aux2_out = nn.Conv2d(32, 2, 1, bias=False)
+
+        self.max_bin = n_fft // 2
+        self.output_bin = n_fft // 2 + 1
+
+        self.offset = 128
+
+    def forward(self, x, aggressiveness=None):
+        mix = x.detach()
+        x = x.clone()
+
+        x = x[:, :, : self.max_bin]
+
+        bandw = x.size()[2] // 2
+        aux1 = torch.cat(
+            [
+                self.stg1_low_band_net(x[:, :, :bandw]),
+                self.stg1_high_band_net(x[:, :, bandw:]),
+            ],
+            dim=2,
+        )
+
+        h = torch.cat([x, aux1], dim=1)
+        aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
+
+        h = torch.cat([x, aux1, aux2], dim=1)
+        h = self.stg3_full_band_net(self.stg3_bridge(h))
+
+        mask = torch.sigmoid(self.out(h))
+        mask = F.pad(
+            input=mask,
+            pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+            mode="replicate",
+        )
+
+        if self.training:
+            aux1 = torch.sigmoid(self.aux1_out(aux1))
+            aux1 = F.pad(
+                input=aux1,
+                pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
+                mode="replicate",
+            )
+            aux2 = torch.sigmoid(self.aux2_out(aux2))
+            aux2 = F.pad(
+                input=aux2,
+                pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
+                mode="replicate",
+            )
+            return mask * mix, aux1 * mix, aux2 * mix
+        else:
+            if aggressiveness:
+                mask[:, :, : aggressiveness["split_bin"]] = torch.pow(
+                    mask[:, :, : aggressiveness["split_bin"]],
+                    1 + aggressiveness["value"] / 3,
+                )
+                mask[:, :, aggressiveness["split_bin"] :] = torch.pow(
+                    mask[:, :, aggressiveness["split_bin"] :],
+                    1 + aggressiveness["value"],
+                )
+
+            return mask * mix
+
+    def predict(self, x_mag, aggressiveness=None):
+        h = self.forward(x_mag, aggressiveness)
+
+        if self.offset > 0:
+            h = h[:, :, :, self.offset : -self.offset]
+            assert h.size()[3] > 0
+
+        return h
diff --git a/rvc/lib/uvr5_pack/lib_v5/nets_new.py b/rvc/lib/uvr5_pack/lib_v5/nets_new.py
new file mode 100644
index 0000000000000000000000000000000000000000..1c0f4fa96d921e979fe31bd4151701b7783fbcea
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/nets_new.py
@@ -0,0 +1,133 @@
+import torch
+import torch.nn.functional as F
+from torch import nn
+
+from . import layers_new
+
+
+class BaseNet(nn.Module):
+    def __init__(
+        self, nin, nout, nin_lstm, nout_lstm, dilations=((4, 2), (8, 4), (12, 6))
+    ):
+        super(BaseNet, self).__init__()
+        self.enc1 = layers_new.Conv2DBNActiv(nin, nout, 3, 1, 1)
+        self.enc2 = layers_new.Encoder(nout, nout * 2, 3, 2, 1)
+        self.enc3 = layers_new.Encoder(nout * 2, nout * 4, 3, 2, 1)
+        self.enc4 = layers_new.Encoder(nout * 4, nout * 6, 3, 2, 1)
+        self.enc5 = layers_new.Encoder(nout * 6, nout * 8, 3, 2, 1)
+
+        self.aspp = layers_new.ASPPModule(nout * 8, nout * 8, dilations, dropout=True)
+
+        self.dec4 = layers_new.Decoder(nout * (6 + 8), nout * 6, 3, 1, 1)
+        self.dec3 = layers_new.Decoder(nout * (4 + 6), nout * 4, 3, 1, 1)
+        self.dec2 = layers_new.Decoder(nout * (2 + 4), nout * 2, 3, 1, 1)
+        self.lstm_dec2 = layers_new.LSTMModule(nout * 2, nin_lstm, nout_lstm)
+        self.dec1 = layers_new.Decoder(nout * (1 + 2) + 1, nout * 1, 3, 1, 1)
+
+    def __call__(self, x):
+        e1 = self.enc1(x)
+        e2 = self.enc2(e1)
+        e3 = self.enc3(e2)
+        e4 = self.enc4(e3)
+        e5 = self.enc5(e4)
+
+        h = self.aspp(e5)
+
+        h = self.dec4(h, e4)
+        h = self.dec3(h, e3)
+        h = self.dec2(h, e2)
+        h = torch.cat([h, self.lstm_dec2(h)], dim=1)
+        h = self.dec1(h, e1)
+
+        return h
+
+
+class CascadedNet(nn.Module):
+    def __init__(self, n_fft, nout=32, nout_lstm=128):
+        super(CascadedNet, self).__init__()
+
+        self.max_bin = n_fft // 2
+        self.output_bin = n_fft // 2 + 1
+        self.nin_lstm = self.max_bin // 2
+        self.offset = 64
+
+        self.stg1_low_band_net = nn.Sequential(
+            BaseNet(2, nout // 2, self.nin_lstm // 2, nout_lstm),
+            layers_new.Conv2DBNActiv(nout // 2, nout // 4, 1, 1, 0),
+        )
+
+        self.stg1_high_band_net = BaseNet(
+            2, nout // 4, self.nin_lstm // 2, nout_lstm // 2
+        )
+
+        self.stg2_low_band_net = nn.Sequential(
+            BaseNet(nout // 4 + 2, nout, self.nin_lstm // 2, nout_lstm),
+            layers_new.Conv2DBNActiv(nout, nout // 2, 1, 1, 0),
+        )
+        self.stg2_high_band_net = BaseNet(
+            nout // 4 + 2, nout // 2, self.nin_lstm // 2, nout_lstm // 2
+        )
+
+        self.stg3_full_band_net = BaseNet(
+            3 * nout // 4 + 2, nout, self.nin_lstm, nout_lstm
+        )
+
+        self.out = nn.Conv2d(nout, 2, 1, bias=False)
+        self.aux_out = nn.Conv2d(3 * nout // 4, 2, 1, bias=False)
+
+    def forward(self, x):
+        x = x[:, :, : self.max_bin]
+
+        bandw = x.size()[2] // 2
+        l1_in = x[:, :, :bandw]
+        h1_in = x[:, :, bandw:]
+        l1 = self.stg1_low_band_net(l1_in)
+        h1 = self.stg1_high_band_net(h1_in)
+        aux1 = torch.cat([l1, h1], dim=2)
+
+        l2_in = torch.cat([l1_in, l1], dim=1)
+        h2_in = torch.cat([h1_in, h1], dim=1)
+        l2 = self.stg2_low_band_net(l2_in)
+        h2 = self.stg2_high_band_net(h2_in)
+        aux2 = torch.cat([l2, h2], dim=2)
+
+        f3_in = torch.cat([x, aux1, aux2], dim=1)
+        f3 = self.stg3_full_band_net(f3_in)
+
+        mask = torch.sigmoid(self.out(f3))
+        mask = F.pad(
+            input=mask,
+            pad=(0, 0, 0, self.output_bin - mask.size()[2]),
+            mode="replicate",
+        )
+
+        if self.training:
+            aux = torch.cat([aux1, aux2], dim=1)
+            aux = torch.sigmoid(self.aux_out(aux))
+            aux = F.pad(
+                input=aux,
+                pad=(0, 0, 0, self.output_bin - aux.size()[2]),
+                mode="replicate",
+            )
+            return mask, aux
+        else:
+            return mask
+
+    def predict_mask(self, x):
+        mask = self.forward(x)
+
+        if self.offset > 0:
+            mask = mask[:, :, :, self.offset : -self.offset]
+            assert mask.size()[3] > 0
+
+        return mask
+
+    def predict(self, x, aggressiveness=None):
+        mask = self.forward(x)
+        pred_mag = x * mask
+
+        if self.offset > 0:
+            pred_mag = pred_mag[:, :, :, self.offset : -self.offset]
+            assert pred_mag.size()[3] > 0
+
+        return pred_mag
diff --git a/rvc/lib/uvr5_pack/lib_v5/spec_utils.py b/rvc/lib/uvr5_pack/lib_v5/spec_utils.py
new file mode 100644
index 0000000000000000000000000000000000000000..e02f02d0c99f9142a6940136adc8afdc33d6a1bd
--- /dev/null
+++ b/rvc/lib/uvr5_pack/lib_v5/spec_utils.py
@@ -0,0 +1,674 @@
+import hashlib
+import json
+import math
+import os
+
+import librosa
+import numpy as np
+import soundfile as sf
+from tqdm import tqdm
+
+
+def crop_center(h1, h2):
+    h1_shape = h1.size()
+    h2_shape = h2.size()
+
+    if h1_shape[3] == h2_shape[3]:
+        return h1
+    elif h1_shape[3] < h2_shape[3]:
+        raise ValueError("h1_shape[3] must be greater than h2_shape[3]")
+
+    # s_freq = (h2_shape[2] - h1_shape[2]) // 2
+    # e_freq = s_freq + h1_shape[2]
+    s_time = (h1_shape[3] - h2_shape[3]) // 2
+    e_time = s_time + h2_shape[3]
+    h1 = h1[:, :, :, s_time:e_time]
+
+    return h1
+
+
+def wave_to_spectrogram(
+    wave, hop_length, n_fft, mid_side=False, mid_side_b2=False, reverse=False
+):
+    if reverse:
+        wave_left = np.flip(np.asfortranarray(wave[0]))
+        wave_right = np.flip(np.asfortranarray(wave[1]))
+    elif mid_side:
+        wave_left = np.asfortranarray(np.add(wave[0], wave[1]) / 2)
+        wave_right = np.asfortranarray(np.subtract(wave[0], wave[1]))
+    elif mid_side_b2:
+        wave_left = np.asfortranarray(np.add(wave[1], wave[0] * 0.5))
+        wave_right = np.asfortranarray(np.subtract(wave[0], wave[1] * 0.5))
+    else:
+        wave_left = np.asfortranarray(wave[0])
+        wave_right = np.asfortranarray(wave[1])
+
+    spec_left = librosa.stft(wave_left, n_fft=n_fft, hop_length=hop_length)
+    spec_right = librosa.stft(wave_right, n_fft=n_fft, hop_length=hop_length)
+
+    spec = np.asfortranarray([spec_left, spec_right])
+
+    return spec
+
+
+def wave_to_spectrogram_mt(
+    wave, hop_length, n_fft, mid_side=False, mid_side_b2=False, reverse=False
+):
+    import threading
+
+    if reverse:
+        wave_left = np.flip(np.asfortranarray(wave[0]))
+        wave_right = np.flip(np.asfortranarray(wave[1]))
+    elif mid_side:
+        wave_left = np.asfortranarray(np.add(wave[0], wave[1]) / 2)
+        wave_right = np.asfortranarray(np.subtract(wave[0], wave[1]))
+    elif mid_side_b2:
+        wave_left = np.asfortranarray(np.add(wave[1], wave[0] * 0.5))
+        wave_right = np.asfortranarray(np.subtract(wave[0], wave[1] * 0.5))
+    else:
+        wave_left = np.asfortranarray(wave[0])
+        wave_right = np.asfortranarray(wave[1])
+
+    def run_thread(**kwargs):
+        global spec_left
+        spec_left = librosa.stft(**kwargs)
+
+    thread = threading.Thread(
+        target=run_thread,
+        kwargs={"y": wave_left, "n_fft": n_fft, "hop_length": hop_length},
+    )
+    thread.start()
+    spec_right = librosa.stft(wave_right, n_fft=n_fft, hop_length=hop_length)
+    thread.join()
+
+    spec = np.asfortranarray([spec_left, spec_right])
+
+    return spec
+
+
+def combine_spectrograms(specs, mp):
+    l = min([specs[i].shape[2] for i in specs])
+    spec_c = np.zeros(shape=(2, mp.param["bins"] + 1, l), dtype=np.complex64)
+    offset = 0
+    bands_n = len(mp.param["band"])
+
+    for d in range(1, bands_n + 1):
+        h = mp.param["band"][d]["crop_stop"] - mp.param["band"][d]["crop_start"]
+        spec_c[:, offset : offset + h, :l] = specs[d][
+            :, mp.param["band"][d]["crop_start"] : mp.param["band"][d]["crop_stop"], :l
+        ]
+        offset += h
+
+    if offset > mp.param["bins"]:
+        raise ValueError("Too much bins")
+
+    # lowpass fiter
+    if (
+        mp.param["pre_filter_start"] > 0
+    ):  # and mp.param['band'][bands_n]['res_type'] in ['scipy', 'polyphase']:
+        if bands_n == 1:
+            spec_c = fft_lp_filter(
+                spec_c, mp.param["pre_filter_start"], mp.param["pre_filter_stop"]
+            )
+        else:
+            gp = 1
+            for b in range(
+                mp.param["pre_filter_start"] + 1, mp.param["pre_filter_stop"]
+            ):
+                g = math.pow(
+                    10, -(b - mp.param["pre_filter_start"]) * (3.5 - gp) / 20.0
+                )
+                gp = g
+                spec_c[:, b, :] *= g
+
+    return np.asfortranarray(spec_c)
+
+
+def spectrogram_to_image(spec, mode="magnitude"):
+    if mode == "magnitude":
+        if np.iscomplexobj(spec):
+            y = np.abs(spec)
+        else:
+            y = spec
+        y = np.log10(y**2 + 1e-8)
+    elif mode == "phase":
+        if np.iscomplexobj(spec):
+            y = np.angle(spec)
+        else:
+            y = spec
+
+    y -= y.min()
+    y *= 255 / y.max()
+    img = np.uint8(y)
+
+    if y.ndim == 3:
+        img = img.transpose(1, 2, 0)
+        img = np.concatenate([np.max(img, axis=2, keepdims=True), img], axis=2)
+
+    return img
+
+
+def reduce_vocal_aggressively(X, y, softmask):
+    v = X - y
+    y_mag_tmp = np.abs(y)
+    v_mag_tmp = np.abs(v)
+
+    v_mask = v_mag_tmp > y_mag_tmp
+    y_mag = np.clip(y_mag_tmp - v_mag_tmp * v_mask * softmask, 0, np.inf)
+
+    return y_mag * np.exp(1.0j * np.angle(y))
+
+
+def mask_silence(mag, ref, thres=0.2, min_range=64, fade_size=32):
+    if min_range < fade_size * 2:
+        raise ValueError("min_range must be >= fade_area * 2")
+
+    mag = mag.copy()
+
+    idx = np.where(ref.mean(axis=(0, 1)) < thres)[0]
+    starts = np.insert(idx[np.where(np.diff(idx) != 1)[0] + 1], 0, idx[0])
+    ends = np.append(idx[np.where(np.diff(idx) != 1)[0]], idx[-1])
+    uninformative = np.where(ends - starts > min_range)[0]
+    if len(uninformative) > 0:
+        starts = starts[uninformative]
+        ends = ends[uninformative]
+        old_e = None
+        for s, e in zip(starts, ends):
+            if old_e is not None and s - old_e < fade_size:
+                s = old_e - fade_size * 2
+
+            if s != 0:
+                weight = np.linspace(0, 1, fade_size)
+                mag[:, :, s : s + fade_size] += weight * ref[:, :, s : s + fade_size]
+            else:
+                s -= fade_size
+
+            if e != mag.shape[2]:
+                weight = np.linspace(1, 0, fade_size)
+                mag[:, :, e - fade_size : e] += weight * ref[:, :, e - fade_size : e]
+            else:
+                e += fade_size
+
+            mag[:, :, s + fade_size : e - fade_size] += ref[
+                :, :, s + fade_size : e - fade_size
+            ]
+            old_e = e
+
+    return mag
+
+
+def align_wave_head_and_tail(a, b):
+    l = min([a[0].size, b[0].size])
+
+    return a[:l, :l], b[:l, :l]
+
+
+def cache_or_load(mix_path, inst_path, mp):
+    mix_basename = os.path.splitext(os.path.basename(mix_path))[0]
+    inst_basename = os.path.splitext(os.path.basename(inst_path))[0]
+
+    cache_dir = "mph{}".format(
+        hashlib.sha1(json.dumps(mp.param, sort_keys=True).encode("utf-8")).hexdigest()
+    )
+    mix_cache_dir = os.path.join("cache", cache_dir)
+    inst_cache_dir = os.path.join("cache", cache_dir)
+
+    os.makedirs(mix_cache_dir, exist_ok=True)
+    os.makedirs(inst_cache_dir, exist_ok=True)
+
+    mix_cache_path = os.path.join(mix_cache_dir, mix_basename + ".npy")
+    inst_cache_path = os.path.join(inst_cache_dir, inst_basename + ".npy")
+
+    if os.path.exists(mix_cache_path) and os.path.exists(inst_cache_path):
+        X_spec_m = np.load(mix_cache_path)
+        y_spec_m = np.load(inst_cache_path)
+    else:
+        X_wave, y_wave, X_spec_s, y_spec_s = {}, {}, {}, {}
+
+        for d in range(len(mp.param["band"]), 0, -1):
+            bp = mp.param["band"][d]
+
+            if d == len(mp.param["band"]):  # high-end band
+                X_wave[d], _ = librosa.load(
+                    mix_path, bp["sr"], False, dtype=np.float32, res_type=bp["res_type"]
+                )
+                y_wave[d], _ = librosa.load(
+                    inst_path,
+                    bp["sr"],
+                    False,
+                    dtype=np.float32,
+                    res_type=bp["res_type"],
+                )
+            else:  # lower bands
+                X_wave[d] = librosa.resample(
+                    X_wave[d + 1],
+                    mp.param["band"][d + 1]["sr"],
+                    bp["sr"],
+                    res_type=bp["res_type"],
+                )
+                y_wave[d] = librosa.resample(
+                    y_wave[d + 1],
+                    mp.param["band"][d + 1]["sr"],
+                    bp["sr"],
+                    res_type=bp["res_type"],
+                )
+
+            X_wave[d], y_wave[d] = align_wave_head_and_tail(X_wave[d], y_wave[d])
+
+            X_spec_s[d] = wave_to_spectrogram(
+                X_wave[d],
+                bp["hl"],
+                bp["n_fft"],
+                mp.param["mid_side"],
+                mp.param["mid_side_b2"],
+                mp.param["reverse"],
+            )
+            y_spec_s[d] = wave_to_spectrogram(
+                y_wave[d],
+                bp["hl"],
+                bp["n_fft"],
+                mp.param["mid_side"],
+                mp.param["mid_side_b2"],
+                mp.param["reverse"],
+            )
+
+        del X_wave, y_wave
+
+        X_spec_m = combine_spectrograms(X_spec_s, mp)
+        y_spec_m = combine_spectrograms(y_spec_s, mp)
+
+        if X_spec_m.shape != y_spec_m.shape:
+            raise ValueError("The combined spectrograms are different: " + mix_path)
+
+        _, ext = os.path.splitext(mix_path)
+
+        np.save(mix_cache_path, X_spec_m)
+        np.save(inst_cache_path, y_spec_m)
+
+    return X_spec_m, y_spec_m
+
+
+def spectrogram_to_wave(spec, hop_length, mid_side, mid_side_b2, reverse):
+    spec_left = np.asfortranarray(spec[0])
+    spec_right = np.asfortranarray(spec[1])
+
+    wave_left = librosa.istft(spec_left, hop_length=hop_length)
+    wave_right = librosa.istft(spec_right, hop_length=hop_length)
+
+    if reverse:
+        return np.asfortranarray([np.flip(wave_left), np.flip(wave_right)])
+    elif mid_side:
+        return np.asfortranarray(
+            [np.add(wave_left, wave_right / 2), np.subtract(wave_left, wave_right / 2)]
+        )
+    elif mid_side_b2:
+        return np.asfortranarray(
+            [
+                np.add(wave_right / 1.25, 0.4 * wave_left),
+                np.subtract(wave_left / 1.25, 0.4 * wave_right),
+            ]
+        )
+    else:
+        return np.asfortranarray([wave_left, wave_right])
+
+
+def spectrogram_to_wave_mt(spec, hop_length, mid_side, reverse, mid_side_b2):
+    import threading
+
+    spec_left = np.asfortranarray(spec[0])
+    spec_right = np.asfortranarray(spec[1])
+
+    def run_thread(**kwargs):
+        global wave_left
+        wave_left = librosa.istft(**kwargs)
+
+    thread = threading.Thread(
+        target=run_thread, kwargs={"stft_matrix": spec_left, "hop_length": hop_length}
+    )
+    thread.start()
+    wave_right = librosa.istft(spec_right, hop_length=hop_length)
+    thread.join()
+
+    if reverse:
+        return np.asfortranarray([np.flip(wave_left), np.flip(wave_right)])
+    elif mid_side:
+        return np.asfortranarray(
+            [np.add(wave_left, wave_right / 2), np.subtract(wave_left, wave_right / 2)]
+        )
+    elif mid_side_b2:
+        return np.asfortranarray(
+            [
+                np.add(wave_right / 1.25, 0.4 * wave_left),
+                np.subtract(wave_left / 1.25, 0.4 * wave_right),
+            ]
+        )
+    else:
+        return np.asfortranarray([wave_left, wave_right])
+
+
+def cmb_spectrogram_to_wave(spec_m, mp, extra_bins_h=None, extra_bins=None):
+    wave_band = {}
+    bands_n = len(mp.param["band"])
+    offset = 0
+
+    for d in range(1, bands_n + 1):
+        bp = mp.param["band"][d]
+        spec_s = np.ndarray(
+            shape=(2, bp["n_fft"] // 2 + 1, spec_m.shape[2]), dtype=complex
+        )
+        h = bp["crop_stop"] - bp["crop_start"]
+        spec_s[:, bp["crop_start"] : bp["crop_stop"], :] = spec_m[
+            :, offset : offset + h, :
+        ]
+
+        offset += h
+        if d == bands_n:  # higher
+            if extra_bins_h:  # if --high_end_process bypass
+                max_bin = bp["n_fft"] // 2
+                spec_s[:, max_bin - extra_bins_h : max_bin, :] = extra_bins[
+                    :, :extra_bins_h, :
+                ]
+            if bp["hpf_start"] > 0:
+                spec_s = fft_hp_filter(spec_s, bp["hpf_start"], bp["hpf_stop"] - 1)
+            if bands_n == 1:
+                wave = spectrogram_to_wave(
+                    spec_s,
+                    bp["hl"],
+                    mp.param["mid_side"],
+                    mp.param["mid_side_b2"],
+                    mp.param["reverse"],
+                )
+            else:
+                wave = np.add(
+                    wave,
+                    spectrogram_to_wave(
+                        spec_s,
+                        bp["hl"],
+                        mp.param["mid_side"],
+                        mp.param["mid_side_b2"],
+                        mp.param["reverse"],
+                    ),
+                )
+        else:
+            sr = mp.param["band"][d + 1]["sr"]
+            if d == 1:  # lower
+                spec_s = fft_lp_filter(spec_s, bp["lpf_start"], bp["lpf_stop"])
+                wave = librosa.resample(
+                    spectrogram_to_wave(
+                        spec_s,
+                        bp["hl"],
+                        mp.param["mid_side"],
+                        mp.param["mid_side_b2"],
+                        mp.param["reverse"],
+                    ),
+                    orig_sr=bp["sr"],
+                    target_sr=sr,
+                    res_type="sinc_fastest",
+                )
+            else:  # mid
+                spec_s = fft_hp_filter(spec_s, bp["hpf_start"], bp["hpf_stop"] - 1)
+                spec_s = fft_lp_filter(spec_s, bp["lpf_start"], bp["lpf_stop"])
+                wave2 = np.add(
+                    wave,
+                    spectrogram_to_wave(
+                        spec_s,
+                        bp["hl"],
+                        mp.param["mid_side"],
+                        mp.param["mid_side_b2"],
+                        mp.param["reverse"],
+                    ),
+                )
+                # wave = librosa.core.resample(wave2, bp['sr'], sr, res_type="sinc_fastest")
+                wave = librosa.core.resample(
+                    wave2, orig_sr=bp["sr"], target_sr=sr, res_type="scipy"
+                )
+
+    return wave.T
+
+
+def fft_lp_filter(spec, bin_start, bin_stop):
+    g = 1.0
+    for b in range(bin_start, bin_stop):
+        g -= 1 / (bin_stop - bin_start)
+        spec[:, b, :] = g * spec[:, b, :]
+
+    spec[:, bin_stop:, :] *= 0
+
+    return spec
+
+
+def fft_hp_filter(spec, bin_start, bin_stop):
+    g = 1.0
+    for b in range(bin_start, bin_stop, -1):
+        g -= 1 / (bin_start - bin_stop)
+        spec[:, b, :] = g * spec[:, b, :]
+
+    spec[:, 0 : bin_stop + 1, :] *= 0
+
+    return spec
+
+
+def mirroring(a, spec_m, input_high_end, mp):
+    if "mirroring" == a:
+        mirror = np.flip(
+            np.abs(
+                spec_m[
+                    :,
+                    mp.param["pre_filter_start"]
+                    - 10
+                    - input_high_end.shape[1] : mp.param["pre_filter_start"]
+                    - 10,
+                    :,
+                ]
+            ),
+            1,
+        )
+        mirror = mirror * np.exp(1.0j * np.angle(input_high_end))
+
+        return np.where(
+            np.abs(input_high_end) <= np.abs(mirror), input_high_end, mirror
+        )
+
+    if "mirroring2" == a:
+        mirror = np.flip(
+            np.abs(
+                spec_m[
+                    :,
+                    mp.param["pre_filter_start"]
+                    - 10
+                    - input_high_end.shape[1] : mp.param["pre_filter_start"]
+                    - 10,
+                    :,
+                ]
+            ),
+            1,
+        )
+        mi = np.multiply(mirror, input_high_end * 1.7)
+
+        return np.where(np.abs(input_high_end) <= np.abs(mi), input_high_end, mi)
+
+
+def ensembling(a, specs):
+    for i in range(1, len(specs)):
+        if i == 1:
+            spec = specs[0]
+
+        ln = min([spec.shape[2], specs[i].shape[2]])
+        spec = spec[:, :, :ln]
+        specs[i] = specs[i][:, :, :ln]
+
+        if "min_mag" == a:
+            spec = np.where(np.abs(specs[i]) <= np.abs(spec), specs[i], spec)
+        if "max_mag" == a:
+            spec = np.where(np.abs(specs[i]) >= np.abs(spec), specs[i], spec)
+
+    return spec
+
+
+def stft(wave, nfft, hl):
+    wave_left = np.asfortranarray(wave[0])
+    wave_right = np.asfortranarray(wave[1])
+    spec_left = librosa.stft(wave_left, nfft, hop_length=hl)
+    spec_right = librosa.stft(wave_right, nfft, hop_length=hl)
+    spec = np.asfortranarray([spec_left, spec_right])
+
+    return spec
+
+
+def istft(spec, hl):
+    spec_left = np.asfortranarray(spec[0])
+    spec_right = np.asfortranarray(spec[1])
+
+    wave_left = librosa.istft(spec_left, hop_length=hl)
+    wave_right = librosa.istft(spec_right, hop_length=hl)
+    wave = np.asfortranarray([wave_left, wave_right])
+
+
+if __name__ == "__main__":
+    import argparse
+    import sys
+    import time
+
+    import cv2
+    from model_param_init import ModelParameters
+
+    p = argparse.ArgumentParser()
+    p.add_argument(
+        "--algorithm",
+        "-a",
+        type=str,
+        choices=["invert", "invert_p", "min_mag", "max_mag", "deep", "align"],
+        default="min_mag",
+    )
+    p.add_argument(
+        "--model_params",
+        "-m",
+        type=str,
+        default=os.path.join("modelparams", "1band_sr44100_hl512.json"),
+    )
+    p.add_argument("--output_name", "-o", type=str, default="output")
+    p.add_argument("--vocals_only", "-v", action="store_true")
+    p.add_argument("input", nargs="+")
+    args = p.parse_args()
+
+    start_time = time.time()
+
+    if args.algorithm.startswith("invert") and len(args.input) != 2:
+        raise ValueError("There should be two input files.")
+
+    if not args.algorithm.startswith("invert") and len(args.input) < 2:
+        raise ValueError("There must be at least two input files.")
+
+    wave, specs = {}, {}
+    mp = ModelParameters(args.model_params)
+
+    for i in range(len(args.input)):
+        spec = {}
+
+        for d in range(len(mp.param["band"]), 0, -1):
+            bp = mp.param["band"][d]
+
+            if d == len(mp.param["band"]):  # high-end band
+                wave[d], _ = librosa.load(
+                    args.input[i],
+                    bp["sr"],
+                    False,
+                    dtype=np.float32,
+                    res_type=bp["res_type"],
+                )
+
+                if len(wave[d].shape) == 1:  # mono to stereo
+                    wave[d] = np.array([wave[d], wave[d]])
+            else:  # lower bands
+                wave[d] = librosa.resample(
+                    wave[d + 1],
+                    mp.param["band"][d + 1]["sr"],
+                    bp["sr"],
+                    res_type=bp["res_type"],
+                )
+
+            spec[d] = wave_to_spectrogram(
+                wave[d],
+                bp["hl"],
+                bp["n_fft"],
+                mp.param["mid_side"],
+                mp.param["mid_side_b2"],
+                mp.param["reverse"],
+            )
+
+        specs[i] = combine_spectrograms(spec, mp)
+
+    del wave
+
+    if args.algorithm == "deep":
+        d_spec = np.where(np.abs(specs[0]) <= np.abs(spec[1]), specs[0], spec[1])
+        v_spec = d_spec - specs[1]
+        sf.write(
+            os.path.join("{}.wav".format(args.output_name)),
+            cmb_spectrogram_to_wave(v_spec, mp),
+            mp.param["sr"],
+        )
+
+    if args.algorithm.startswith("invert"):
+        ln = min([specs[0].shape[2], specs[1].shape[2]])
+        specs[0] = specs[0][:, :, :ln]
+        specs[1] = specs[1][:, :, :ln]
+
+        if "invert_p" == args.algorithm:
+            X_mag = np.abs(specs[0])
+            y_mag = np.abs(specs[1])
+            max_mag = np.where(X_mag >= y_mag, X_mag, y_mag)
+            v_spec = specs[1] - max_mag * np.exp(1.0j * np.angle(specs[0]))
+        else:
+            specs[1] = reduce_vocal_aggressively(specs[0], specs[1], 0.2)
+            v_spec = specs[0] - specs[1]
+
+            if not args.vocals_only:
+                X_mag = np.abs(specs[0])
+                y_mag = np.abs(specs[1])
+                v_mag = np.abs(v_spec)
+
+                X_image = spectrogram_to_image(X_mag)
+                y_image = spectrogram_to_image(y_mag)
+                v_image = spectrogram_to_image(v_mag)
+
+                cv2.imwrite("{}_X.png".format(args.output_name), X_image)
+                cv2.imwrite("{}_y.png".format(args.output_name), y_image)
+                cv2.imwrite("{}_v.png".format(args.output_name), v_image)
+
+                sf.write(
+                    "{}_X.wav".format(args.output_name),
+                    cmb_spectrogram_to_wave(specs[0], mp),
+                    mp.param["sr"],
+                )
+                sf.write(
+                    "{}_y.wav".format(args.output_name),
+                    cmb_spectrogram_to_wave(specs[1], mp),
+                    mp.param["sr"],
+                )
+
+        sf.write(
+            "{}_v.wav".format(args.output_name),
+            cmb_spectrogram_to_wave(v_spec, mp),
+            mp.param["sr"],
+        )
+    else:
+        if not args.algorithm == "deep":
+            sf.write(
+                os.path.join("ensembled", "{}.wav".format(args.output_name)),
+                cmb_spectrogram_to_wave(ensembling(args.algorithm, specs), mp),
+                mp.param["sr"],
+            )
+
+    if args.algorithm == "align":
+        trackalignment = [
+            {
+                "file1": '"{}"'.format(args.input[0]),
+                "file2": '"{}"'.format(args.input[1]),
+            }
+        ]
+
+        for i, e in tqdm(enumerate(trackalignment), desc="Performing Alignment..."):
+            os.system(f"python lib/align_tracks.py {e['file1']} {e['file2']}")
+
+    # print('Total time: {0:.{1}f}s'.format(time.time() - start_time, 1))
diff --git a/rvc/lib/uvr5_pack/name_params.json b/rvc/lib/uvr5_pack/name_params.json
new file mode 100644
index 0000000000000000000000000000000000000000..8ed51a68370607a7a8693b99cfb35fc5d92b04af
--- /dev/null
+++ b/rvc/lib/uvr5_pack/name_params.json
@@ -0,0 +1,263 @@
+{
+    "equivalent" : [
+        {
+            "model_hash_name" : [
+                {
+                    "hash_name": "47939caf0cfe52a0e81442b85b971dfd",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_44100.json",
+                    "param_name": "4band_44100"
+                },
+                {
+                    "hash_name": "4e4ecb9764c50a8c414fee6e10395bbe",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_v2.json",
+                    "param_name": "4band_v2"
+                },
+                {
+                    "hash_name": "ca106edd563e034bde0bdec4bb7a4b36",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_v2.json",
+                    "param_name": "4band_v2"
+                },
+                {
+                    "hash_name": "e60a1e84803ce4efc0a6551206cc4b71",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_44100.json",
+                    "param_name": "4band_44100"
+                },
+                {
+                    "hash_name": "a82f14e75892e55e994376edbf0c8435",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_44100.json",
+                    "param_name": "4band_44100"
+                },
+                {
+                    "hash_name": "6dd9eaa6f0420af9f1d403aaafa4cc06",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_v2_sn.json",
+                    "param_name": "4band_v2_sn"
+                },
+                {
+                    "hash_name": "08611fb99bd59eaa79ad27c58d137727",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_v2_sn.json",
+                    "param_name": "4band_v2_sn"
+                },
+                {
+                    "hash_name": "5c7bbca45a187e81abbbd351606164e5",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/3band_44100_msb2.json",
+                    "param_name": "3band_44100_msb2"
+                },
+                {
+                    "hash_name": "d6b2cb685a058a091e5e7098192d3233",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/3band_44100_msb2.json",
+                    "param_name": "3band_44100_msb2"
+                },
+                {
+                    "hash_name": "c1b9f38170a7c90e96f027992eb7c62b",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_44100.json",
+                    "param_name": "4band_44100"
+                },
+                {
+                    "hash_name": "c3448ec923fa0edf3d03a19e633faa53",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_44100.json",
+                    "param_name": "4band_44100"
+                },
+                {
+                    "hash_name": "68aa2c8093d0080704b200d140f59e54",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/3band_44100.json",
+                    "param_name": "3band_44100"
+                },
+                {
+                    "hash_name": "fdc83be5b798e4bd29fe00fe6600e147",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/3band_44100_mid.json",
+                    "param_name": "3band_44100_mid.json"
+                },
+                {
+                    "hash_name": "2ce34bc92fd57f55db16b7a4def3d745",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/3band_44100_mid.json",
+                    "param_name": "3band_44100_mid.json"
+                },
+                {
+                    "hash_name": "52fdca89576f06cf4340b74a4730ee5f",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_44100.json",
+                    "param_name": "4band_44100.json"
+                },
+                {
+                    "hash_name": "41191165b05d38fc77f072fa9e8e8a30",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_44100.json",
+                    "param_name": "4band_44100.json"
+                },
+                {
+                    "hash_name": "89e83b511ad474592689e562d5b1f80e",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/2band_32000.json",
+                    "param_name": "2band_32000.json"
+                },
+                {
+                    "hash_name": "0b954da81d453b716b114d6d7c95177f",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/2band_32000.json",
+                    "param_name": "2band_32000.json"
+                }
+
+            ],
+            "v4 Models": [
+                {
+                    "hash_name": "6a00461c51c2920fd68937d4609ed6c8",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/1band_sr16000_hl512.json",
+                    "param_name": "1band_sr16000_hl512"
+                },
+                {
+                    "hash_name": "0ab504864d20f1bd378fe9c81ef37140",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json",
+                    "param_name": "1band_sr32000_hl512"
+                },
+                {
+                    "hash_name": "7dd21065bf91c10f7fccb57d7d83b07f",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json",
+                    "param_name": "1band_sr32000_hl512"
+                },
+                {
+                    "hash_name": "80ab74d65e515caa3622728d2de07d23",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json",
+                    "param_name": "1band_sr32000_hl512"
+                },
+                {
+                    "hash_name": "edc115e7fc523245062200c00caa847f",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/1band_sr33075_hl384.json",
+                    "param_name": "1band_sr33075_hl384"
+                },
+                {
+                    "hash_name": "28063e9f6ab5b341c5f6d3c67f2045b7",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/1band_sr33075_hl384.json",
+                    "param_name": "1band_sr33075_hl384"
+                },
+                {
+                    "hash_name": "b58090534c52cbc3e9b5104bad666ef2",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512.json",
+                    "param_name": "1band_sr44100_hl512"
+                },
+                {
+                    "hash_name": "0cdab9947f1b0928705f518f3c78ea8f",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512.json",
+                    "param_name": "1band_sr44100_hl512"
+                },
+                {
+                    "hash_name": "ae702fed0238afb5346db8356fe25f13",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl1024.json",
+                    "param_name": "1band_sr44100_hl1024"
+                }
+            ]
+        }
+    ],
+    "User Models" : [
+        {
+            "1 Band": [
+                {
+                    "hash_name": "1band_sr16000_hl512",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/1band_sr16000_hl512.json",
+                    "param_name": "1band_sr16000_hl512"
+                },
+                {
+                    "hash_name": "1band_sr32000_hl512",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/1band_sr32000_hl512.json",
+                    "param_name": "1band_sr16000_hl512"
+                },
+                {
+                    "hash_name": "1band_sr33075_hl384",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/1band_sr33075_hl384.json",
+                    "param_name": "1band_sr33075_hl384"
+                },
+                {
+                    "hash_name": "1band_sr44100_hl256",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl256.json",
+                    "param_name": "1band_sr44100_hl256"
+                },
+                {
+                    "hash_name": "1band_sr44100_hl512",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl512.json",
+                    "param_name": "1band_sr44100_hl512"
+                },
+                {
+                    "hash_name": "1band_sr44100_hl1024",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/1band_sr44100_hl1024.json",
+                    "param_name": "1band_sr44100_hl1024"
+                }
+            ],
+            "2 Band": [
+                {
+                    "hash_name": "2band_44100_lofi",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/2band_44100_lofi.json",
+                    "param_name": "2band_44100_lofi"
+                },
+                {
+                    "hash_name": "2band_32000",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/2band_32000.json",
+                    "param_name": "2band_32000"
+                },
+                {
+                    "hash_name": "2band_48000",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/2band_48000.json",
+                    "param_name": "2band_48000"
+                }
+            ],
+            "3 Band": [
+                {
+                    "hash_name": "3band_44100",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/3band_44100.json",
+                    "param_name": "3band_44100"
+                },
+                {
+                    "hash_name": "3band_44100_mid",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/3band_44100_mid.json",
+                    "param_name": "3band_44100_mid"
+                },
+                {
+                    "hash_name": "3band_44100_msb2",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/3band_44100_msb2.json",
+                    "param_name": "3band_44100_msb2"
+                }
+            ],
+            "4 Band": [
+                {
+                    "hash_name": "4band_44100",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_44100.json",
+                    "param_name": "4band_44100"
+                },
+                {
+                    "hash_name": "4band_44100_mid",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_44100_mid.json",
+                    "param_name": "4band_44100_mid"
+                },
+                {
+                    "hash_name": "4band_44100_msb",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_44100_msb.json",
+                    "param_name": "4band_44100_msb"
+                },
+                {
+                    "hash_name": "4band_44100_msb2",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_44100_msb2.json",
+                    "param_name": "4band_44100_msb2"
+                },
+                {
+                    "hash_name": "4band_44100_reverse",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_44100_reverse.json",
+                    "param_name": "4band_44100_reverse"
+                },
+                {
+                    "hash_name": "4band_44100_sw",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_44100_sw.json",
+                    "param_name": "4band_44100_sw"
+                },
+                {
+                    "hash_name": "4band_v2",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_v2.json",
+                    "param_name": "4band_v2"
+                },
+                {
+                    "hash_name": "4band_v2_sn",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/4band_v2_sn.json",
+                    "param_name": "4band_v2_sn"
+                },
+                {
+                    "hash_name": "tmodelparam",
+                    "model_params": "infer/lib/uvr5_pack/lib_v5/modelparams/tmodelparam.json",
+                    "param_name": "User Model Param Set"
+                }
+            ]
+        }
+    ]
+}
\ No newline at end of file
diff --git a/rvc/lib/uvr5_pack/utils.py b/rvc/lib/uvr5_pack/utils.py
new file mode 100644
index 0000000000000000000000000000000000000000..ac7391544689ec812cc0cb321e0de6abb130e6ba
--- /dev/null
+++ b/rvc/lib/uvr5_pack/utils.py
@@ -0,0 +1,121 @@
+import json
+
+import numpy as np
+import torch
+from tqdm import tqdm
+
+
+def load_data(file_name: str = "./rvc/lib/uvr5_pack/name_params.json") -> dict:
+    with open(file_name, "r") as f:
+        data = json.load(f)
+
+    return data
+
+
+def make_padding(width, cropsize, offset):
+    left = offset
+    roi_size = cropsize - left * 2
+    if roi_size == 0:
+        roi_size = cropsize
+    right = roi_size - (width % roi_size) + left
+
+    return left, right, roi_size
+
+
+def inference(X_spec, device, model, aggressiveness, data):
+    """
+    data ： dic configs
+    """
+
+    def _execute(
+        X_mag_pad, roi_size, n_window, device, model, aggressiveness, is_half=True
+    ):
+        model.eval()
+        with torch.no_grad():
+            preds = []
+
+            iterations = [n_window]
+
+            total_iterations = sum(iterations)
+            for i in tqdm(range(n_window)):
+                start = i * roi_size
+                X_mag_window = X_mag_pad[
+                    None, :, :, start : start + data["window_size"]
+                ]
+                X_mag_window = torch.from_numpy(X_mag_window)
+                if is_half:
+                    X_mag_window = X_mag_window.half()
+                X_mag_window = X_mag_window.to(device)
+
+                pred = model.predict(X_mag_window, aggressiveness)
+
+                pred = pred.detach().cpu().numpy()
+                preds.append(pred[0])
+
+            pred = np.concatenate(preds, axis=2)
+        return pred
+
+    def preprocess(X_spec):
+        X_mag = np.abs(X_spec)
+        X_phase = np.angle(X_spec)
+
+        return X_mag, X_phase
+
+    X_mag, X_phase = preprocess(X_spec)
+
+    coef = X_mag.max()
+    X_mag_pre = X_mag / coef
+
+    n_frame = X_mag_pre.shape[2]
+    pad_l, pad_r, roi_size = make_padding(n_frame, data["window_size"], model.offset)
+    n_window = int(np.ceil(n_frame / roi_size))
+
+    X_mag_pad = np.pad(X_mag_pre, ((0, 0), (0, 0), (pad_l, pad_r)), mode="constant")
+
+    if list(model.state_dict().values())[0].dtype == torch.float16:
+        is_half = True
+    else:
+        is_half = False
+    pred = _execute(
+        X_mag_pad, roi_size, n_window, device, model, aggressiveness, is_half
+    )
+    pred = pred[:, :, :n_frame]
+
+    if data["tta"]:
+        pad_l += roi_size // 2
+        pad_r += roi_size // 2
+        n_window += 1
+
+        X_mag_pad = np.pad(X_mag_pre, ((0, 0), (0, 0), (pad_l, pad_r)), mode="constant")
+
+        pred_tta = _execute(
+            X_mag_pad, roi_size, n_window, device, model, aggressiveness, is_half
+        )
+        pred_tta = pred_tta[:, :, roi_size // 2 :]
+        pred_tta = pred_tta[:, :, :n_frame]
+
+        return (pred + pred_tta) * 0.5 * coef, X_mag, np.exp(1.0j * X_phase)
+    else:
+        return pred * coef, X_mag, np.exp(1.0j * X_phase)
+
+
+def _get_name_params(model_path, model_hash):
+    data = load_data()
+    flag = False
+    ModelName = model_path
+    for type in list(data):
+        for model in list(data[type][0]):
+            for i in range(len(data[type][0][model])):
+                if str(data[type][0][model][i]["hash_name"]) == model_hash:
+                    flag = True
+                elif str(data[type][0][model][i]["hash_name"]) in ModelName:
+                    flag = True
+
+                if flag:
+                    model_params_auto = data[type][0][model][i]["model_params"]
+                    param_name_auto = data[type][0][model][i]["param_name"]
+                    if type == "equivalent":
+                        return param_name_auto, model_params_auto
+                    else:
+                        flag = False
+    return param_name_auto, model_params_auto
diff --git a/rvc/modules/onnx/export.py b/rvc/modules/onnx/export.py
new file mode 100644
index 0000000000000000000000000000000000000000..6aa7140edab4213eb46766eb6801518d0f2209a4
--- /dev/null
+++ b/rvc/modules/onnx/export.py
@@ -0,0 +1,54 @@
+import torch
+
+from rvc.lib.infer_pack.models_onnx import SynthesizerTrnMsNSFsidM
+
+
+def export_onnx(ModelPath, ExportedPath):
+    cpt = torch.load(ModelPath, map_location="cpu")
+    cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0]
+    vec_channels = 256 if cpt.get("version", "v1") == "v1" else 768
+
+    test_phone = torch.rand(1, 200, vec_channels)  # hidden unit
+    test_phone_lengths = torch.tensor(
+        [200]
+    ).long()  # hidden unit length (doesn't seem to help)）
+    test_pitch = torch.randint(size=(1, 200), low=5, high=255)  # Base frequency (in Hz)
+    test_pitchf = torch.rand(1, 200)  # nsf base frequency
+    test_ds = torch.LongTensor([0])  # Speaker ID
+    test_rnd = torch.rand(1, 192, 200)  # Noise (add random factor)
+
+    device = "cpu"  # Device on export (does not affect use of model)
+
+    net_g = SynthesizerTrnMsNSFsidM(
+        *cpt["config"], is_half=False, version=cpt.get("version", "v1")
+    )  # fp32 export (C++ has to manually rearrange memory to support fp16 so no fp16 for now)
+    net_g.load_state_dict(cpt["weight"], strict=False)
+    input_names = ["phone", "phone_lengths", "pitch", "pitchf", "ds", "rnd"]
+    output_names = [
+        "audio",
+    ]
+    # net_g.construct_spkmixmap(n_speaker) Multi-Role Mixed Track Export
+    torch.onnx.export(
+        net_g,
+        (
+            test_phone.to(device),
+            test_phone_lengths.to(device),
+            test_pitch.to(device),
+            test_pitchf.to(device),
+            test_ds.to(device),
+            test_rnd.to(device),
+        ),
+        ExportedPath,
+        dynamic_axes={
+            "phone": [1],
+            "pitch": [1],
+            "pitchf": [1],
+            "rnd": [2],
+        },
+        do_constant_folding=False,
+        opset_version=13,
+        verbose=False,
+        input_names=input_names,
+        output_names=output_names,
+    )
+    return "Finished"
diff --git a/rvc/modules/uvr5/mdxnet.py b/rvc/modules/uvr5/mdxnet.py
new file mode 100644
index 0000000000000000000000000000000000000000..f339cd38821bcae827d1ca616998e76b949d24ea
--- /dev/null
+++ b/rvc/modules/uvr5/mdxnet.py
@@ -0,0 +1,256 @@
+import logging
+import os
+
+import librosa
+import numpy as np
+import soundfile as sf
+import torch
+from tqdm import tqdm
+
+cpu = torch.device("cpu")
+
+logger: logging.Logger = logging.getLogger(__name__)
+
+
+class ConvTDFNetTrim:
+    def __init__(
+        self, device, model_name, target_name, L, dim_f, dim_t, n_fft, hop=1024
+    ):
+        super(ConvTDFNetTrim, self).__init__()
+
+        self.dim_f = dim_f
+        self.dim_t = 2**dim_t
+        self.n_fft = n_fft
+        self.hop = hop
+        self.n_bins = self.n_fft // 2 + 1
+        self.chunk_size = hop * (self.dim_t - 1)
+        self.window = torch.hann_window(window_length=self.n_fft, periodic=True).to(
+            device
+        )
+        self.target_name = target_name
+        self.blender = "blender" in model_name
+
+        self.dim_c = 4
+        out_c = self.dim_c * 4 if target_name == "*" else self.dim_c
+        self.freq_pad = torch.zeros(
+            [1, out_c, self.n_bins - self.dim_f, self.dim_t]
+        ).to(device)
+
+        self.n = L // 2
+
+    def stft(self, x):
+        x = x.reshape([-1, self.chunk_size])
+        x = torch.stft(
+            x,
+            n_fft=self.n_fft,
+            hop_length=self.hop,
+            window=self.window,
+            center=True,
+            return_complex=True,
+        )
+        x = torch.view_as_real(x)
+        x = x.permute([0, 3, 1, 2])
+        x = x.reshape([-1, 2, 2, self.n_bins, self.dim_t]).reshape(
+            [-1, self.dim_c, self.n_bins, self.dim_t]
+        )
+        return x[:, :, : self.dim_f]
+
+    def istft(self, x, freq_pad=None):
+        freq_pad = (
+            self.freq_pad.repeat([x.shape[0], 1, 1, 1])
+            if freq_pad is None
+            else freq_pad
+        )
+        x = torch.cat([x, freq_pad], -2)
+        c = 4 * 2 if self.target_name == "*" else 2
+        x = x.reshape([-1, c, 2, self.n_bins, self.dim_t]).reshape(
+            [-1, 2, self.n_bins, self.dim_t]
+        )
+        x = x.permute([0, 2, 3, 1])
+        x = x.contiguous()
+        x = torch.view_as_complex(x)
+        x = torch.istft(
+            x, n_fft=self.n_fft, hop_length=self.hop, window=self.window, center=True
+        )
+        return x.reshape([-1, c, self.chunk_size])
+
+
+def get_models(device, dim_f, dim_t, n_fft):
+    return ConvTDFNetTrim(
+        device=device,
+        model_name="Conv-TDF",
+        target_name="vocals",
+        L=11,
+        dim_f=dim_f,
+        dim_t=dim_t,
+        n_fft=n_fft,
+    )
+
+
+class Predictor:
+    def __init__(self, args):
+        import onnxruntime as ort
+
+        logger.info(ort.get_available_providers())
+        self.args = args
+        self.model_ = get_models(
+            device=cpu, dim_f=args.dim_f, dim_t=args.dim_t, n_fft=args.n_fft
+        )
+        self.model = ort.InferenceSession(
+            os.path.join(args.onnx, self.model_.target_name + ".onnx"),
+            providers=[
+                "CUDAExecutionProvider",
+                "DmlExecutionProvider",
+                "CPUExecutionProvider",
+            ],
+        )
+        logger.info("ONNX load done")
+
+    def demix(self, mix):
+        samples = mix.shape[-1]
+        margin = self.args.margin
+        chunk_size = self.args.chunks * 44100
+        assert not margin == 0, "margin cannot be zero!"
+        if margin > chunk_size:
+            margin = chunk_size
+
+        segmented_mix = {}
+
+        if self.args.chunks == 0 or samples < chunk_size:
+            chunk_size = samples
+
+        counter = -1
+        for skip in range(0, samples, chunk_size):
+            counter += 1
+
+            s_margin = 0 if counter == 0 else margin
+            end = min(skip + chunk_size + margin, samples)
+
+            start = skip - s_margin
+
+            segmented_mix[skip] = mix[:, start:end].copy()
+            if end == samples:
+                break
+
+        sources = self.demix_base(segmented_mix, margin_size=margin)
+        """
+        mix:(2,big_sample)
+        segmented_mix:offset->(2,small_sample)
+        sources:(1,2,big_sample)
+        """
+        return sources
+
+    def demix_base(self, mixes, margin_size):
+        chunked_sources = []
+        progress_bar = tqdm(total=len(mixes))
+        progress_bar.set_description("Processing")
+        for mix in mixes:
+            cmix = mixes[mix]
+            sources = []
+            n_sample = cmix.shape[1]
+            model = self.model_
+            trim = model.n_fft // 2
+            gen_size = model.chunk_size - 2 * trim
+            pad = gen_size - n_sample % gen_size
+            mix_p = np.concatenate(
+                (np.zeros((2, trim)), cmix, np.zeros((2, pad)), np.zeros((2, trim))), 1
+            )
+            mix_waves = []
+            i = 0
+            while i < n_sample + pad:
+                waves = np.array(mix_p[:, i : i + model.chunk_size])
+                mix_waves.append(waves)
+                i += gen_size
+            mix_waves = torch.tensor(mix_waves, dtype=torch.float32).to(cpu)
+            with torch.no_grad():
+                _ort = self.model
+                spek = model.stft(mix_waves)
+                if self.args.denoise:
+                    spec_pred = (
+                        -_ort.run(None, {"input": -spek.cpu().numpy()})[0] * 0.5
+                        + _ort.run(None, {"input": spek.cpu().numpy()})[0] * 0.5
+                    )
+                    tar_waves = model.istft(torch.tensor(spec_pred))
+                else:
+                    tar_waves = model.istft(
+                        torch.tensor(_ort.run(None, {"input": spek.cpu().numpy()})[0])
+                    )
+                tar_signal = (
+                    tar_waves[:, :, trim:-trim]
+                    .transpose(0, 1)
+                    .reshape(2, -1)
+                    .numpy()[:, :-pad]
+                )
+
+                start = 0 if mix == 0 else margin_size
+                end = None if mix == list(mixes.keys())[::-1][0] else -margin_size
+                if margin_size == 0:
+                    end = None
+                sources.append(tar_signal[:, start:end])
+
+                progress_bar.update(1)
+
+            chunked_sources.append(sources)
+        _sources = np.concatenate(chunked_sources, axis=-1)
+        # del self.model
+        progress_bar.close()
+        return _sources
+
+    def prediction(self, m, vocal_root, others_root, format):
+        os.makedirs(vocal_root, exist_ok=True)
+        os.makedirs(others_root, exist_ok=True)
+        basename = os.path.basename(m)
+        mix, rate = librosa.load(m, mono=False, sr=44100)
+        if mix.ndim == 1:
+            mix = np.asfortranarray([mix, mix])
+        mix = mix.T
+        sources = self.demix(mix.T)
+        opt = sources[0].T
+        if format in ["wav", "flac"]:
+            sf.write(
+                "%s/%s_main_vocal.%s" % (vocal_root, basename, format), mix - opt, rate
+            )
+            sf.write("%s/%s_others.%s" % (others_root, basename, format), opt, rate)
+        else:
+            path_vocal = "%s/%s_main_vocal.wav" % (vocal_root, basename)
+            path_other = "%s/%s_others.wav" % (others_root, basename)
+            sf.write(path_vocal, mix - opt, rate)
+            sf.write(path_other, opt, rate)
+            opt_path_vocal = path_vocal[:-4] + ".%s" % format
+            opt_path_other = path_other[:-4] + ".%s" % format
+            if os.path.exists(path_vocal):
+                os.system(
+                    "ffmpeg -i %s -vn %s -q:a 2 -y" % (path_vocal, opt_path_vocal)
+                )
+                if os.path.exists(opt_path_vocal):
+                    try:
+                        os.remove(path_vocal)
+                    except Exception:
+                        pass
+            if os.path.exists(path_other):
+                os.system(
+                    "ffmpeg -i %s -vn %s -q:a 2 -y" % (path_other, opt_path_other)
+                )
+                if os.path.exists(opt_path_other):
+                    try:
+                        os.remove(path_other)
+                    except Exception:
+                        pass
+
+
+class MDXNetDereverb:
+    def __init__(self, chunks, device):
+        self.onnx = "assets/uvr5_weights/onnx_dereverb_By_FoxJoy"
+        self.shifts = 10  # 'Predict with randomised equivariant stabilisation'
+        self.mixing = "min_mag"  # ['default','min_mag','max_mag']
+        self.chunks = chunks  # 15
+        self.margin = 44100
+        self.dim_t = 9
+        self.dim_f = 3072
+        self.n_fft = 6144
+        self.denoise = True
+        self.pred = Predictor(self)
+        self.device = device
+
+    def _path_audio_(self, input, vocal_root, others_root, format, is_hp3=False):
+        self.pred.prediction(input, vocal_root, others_root, format)
diff --git a/rvc/modules/uvr5/modules.py b/rvc/modules/uvr5/modules.py
new file mode 100644
index 0000000000000000000000000000000000000000..abebfb5790f8891e62d0906294f0b2be2d89041a
--- /dev/null
+++ b/rvc/modules/uvr5/modules.py
@@ -0,0 +1,76 @@
+import logging
+import os
+import traceback
+from glob import glob
+from pathlib import Path
+
+import soundfile as sf
+import torch
+from pydub import AudioSegment
+
+from rvc.configs.config import Config
+from rvc.modules.uvr5.mdxnet import MDXNetDereverb
+from rvc.modules.uvr5.vr import AudioPreprocess
+
+logger: logging.Logger = logging.getLogger(__name__)
+
+
+class UVR:
+    def __init__(self):
+        self.need_reformat: bool = True
+        self.config: Config = Config()
+
+    def uvr_wrapper(
+        self,
+        audio_path: Path,
+        agg: int = 10,
+        model_name: str | None = None,
+        temp_dir: Path | None = None,
+    ):
+        infos = list()
+        if model_name is None:
+            model_name = os.path.basename(glob(f"{os.getenv('weight_uvr5_root')}/*")[0])
+
+        pre_fun = AudioPreprocess(
+            os.path.join(os.getenv("weight_uvr5_root"), model_name),  # + ".pth"
+            int(agg),
+        )
+
+        process_paths = (
+            [
+                _
+                for _ in glob(f"{audio_path}/*")
+                if os.path.splitext(_)[-1][1:].upper() in sf.available_formats()
+            ]
+            if os.path.isdir(audio_path)
+            else audio_path
+        )
+
+        results = []
+
+        for process_path in [process_paths]:
+            print(f"path: {process_path}")
+            info = sf.info(process_path)
+            if not (info.channels == 2 and info.samplerate == "44100"):
+                tmp_path = os.path.join(
+                    temp_dir or os.environ.get("TEMP"), os.path.basename(process_path)
+                )
+                AudioSegment.from_file(process_path).export(
+                    tmp_path,
+                    format="wav",
+                    codec="pcm_s16le",
+                    bitrate="16k",
+                    parameters=["-ar", "44100"],
+                )
+
+            results.append(
+                pre_fun.process(
+                    tmp_path or process_path,
+                )
+            )
+            infos.append(f"{os.path.basename(process_path)}->Success")
+
+        if torch.cuda.is_available():
+            torch.cuda.empty_cache()
+
+        return results
diff --git a/rvc/modules/uvr5/vr.py b/rvc/modules/uvr5/vr.py
new file mode 100644
index 0000000000000000000000000000000000000000..caebe31b103067be0e3166261d96f2951c0f598f
--- /dev/null
+++ b/rvc/modules/uvr5/vr.py
@@ -0,0 +1,137 @@
+import logging
+import os
+
+import librosa
+import numpy as np
+import soundfile as sf
+import torch
+
+from rvc.configs.config import Config
+from rvc.lib.uvr5_pack.lib_v5 import nets_61968KB as Nets
+from rvc.lib.uvr5_pack.lib_v5 import spec_utils
+from rvc.lib.uvr5_pack.lib_v5.model_param_init import ModelParameters
+from rvc.lib.uvr5_pack.lib_v5.nets_new import CascadedNet
+from rvc.lib.uvr5_pack.utils import inference
+
+logger = logging.getLogger(__name__)
+
+
+class AudioPreprocess:
+    def __init__(self, model_path, agg, tta=False):
+        self.model_path = model_path
+        self.data = {
+            # Processing Options
+            "postprocess": False,
+            "tta": tta,
+            # Constants
+            "window_size": 512,
+            "agg": agg,
+            "high_end_process": "mirroring",
+        }
+        self.config: Config = Config()
+        self.version = 3 if "DeEcho" not in self.model_path else 2
+        self.mp: ModelParameters = ModelParameters(
+            f"rvc/lib/uvr5_pack/lib_v5/modelparams/4band_v{self.version}.json"
+        )
+        self.model = (
+            Nets.CascadedASPPNet(self.mp.param["bins"] * 2)
+            if self.version == 3
+            else CascadedNet(
+                self.mp.param["bins"] * 2, 64 if "DeReverb" in model_path else 48
+            )
+            .load_state_dict(torch.load(model_path, map_location="cpu"))
+            .eval()
+        )
+        if self.config.is_half:
+            self.model = self.model.half()
+        self.model.to(self.config.device)
+
+    def process(
+        self,
+        music_file,
+    ):
+        x_wave, y_wave, x_spec_s, y_spec_s = {}, {}, {}, {}
+        bands_n = len(self.mp.param["band"])
+
+        for d in range(bands_n, 0, -1):
+            bp = self.mp.param["band"][d]
+            if d == bands_n:  # high-end band
+                # librosa loading may be buggy for some audio. ffmpeg will solve this, but it's a pain
+                x_wave[d] = librosa.core.load(
+                    music_file,
+                    sr=bp["sr"],
+                    mono=False,
+                    dtype=np.float32,
+                    res_type=bp["res_type"],
+                )[0]
+                if x_wave[d].ndim == 1:
+                    x_wave[d] = np.asfortranarray([x_wave[d], x_wave[d]])
+            else:  # lower bands
+                x_wave[d] = librosa.core.resample(
+                    x_wave[d + 1],
+                    orig_sr=self.mp.param["band"][d + 1]["sr"],
+                    target_sr=bp["sr"],
+                    res_type=bp["res_type"],
+                )
+            # Stft of wave source
+            x_spec_s[d] = spec_utils.wave_to_spectrogram_mt(
+                x_wave[d],
+                bp["hl"],
+                bp["n_fft"],
+                self.mp.param["mid_side"],
+                self.mp.param["mid_side_b2"],
+                self.mp.param["reverse"],
+            )
+
+            # pdb.set_trace()
+
+        input_high_end_h = (
+            self.mp.param["band"][1]["n_fft"] // 2
+            - self.mp.param["band"][1]["crop_stop"]
+        ) + (self.mp.param["pre_filter_stop"] - self.mp.param["pre_filter_start"])
+        input_high_end = x_spec_s[1][
+            :,
+            self.mp.param["band"][1]["n_fft"] // 2
+            - input_high_end_h : self.mp.param["band"][1]["n_fft"] // 2,
+            :,
+        ]
+        x_spec_m = spec_utils.combine_spectrograms(x_spec_s, self.mp)
+        aggresive_set = float(self.data["agg"] / 100)
+        aggressiveness = {
+            "value": aggresive_set,
+            "split_bin": self.mp.param["band"][1]["crop_stop"],
+        }
+        with torch.no_grad():
+            pred, x_mag, x_phase = inference(
+                x_spec_m, self.config.device, self.model, aggressiveness, self.data
+            )
+        # Postprocess
+        if self.data["postprocess"]:
+            pred_inv = np.clip(x_mag - pred, 0, np.inf)
+            pred = spec_utils.mask_silence(pred, pred_inv)
+        y_spec_m = pred * x_phase
+        v_spec_m = x_spec_m - y_spec_m
+
+        if self.data["high_end_process"].startswith("mirroring"):
+            input_high_end_ = spec_utils.mirroring(
+                self.data["high_end_process"], y_spec_m, input_high_end, self.mp
+            )
+            wav_instrument = spec_utils.cmb_spectrogram_to_wave(
+                y_spec_m, self.mp, input_high_end_h, input_high_end_
+            )
+            input_high_end_ = spec_utils.mirroring(
+                self.data["high_end_process"], v_spec_m, input_high_end, self.mp
+            )
+            wav_vocals = spec_utils.cmb_spectrogram_to_wave(
+                v_spec_m, self.mp, input_high_end_h, input_high_end_
+            )
+        else:
+            wav_instrument = spec_utils.cmb_spectrogram_to_wave(y_spec_m, self.mp)
+            wav_vocals = spec_utils.cmb_spectrogram_to_wave(v_spec_m, self.mp)
+
+        return (
+            (np.array(wav_instrument) * 32768).astype("int16"),
+            (np.array(wav_vocals) * 32768).astype("int16"),
+            self.mp.param["sr"],
+            self.data["agg"],
+        )
diff --git a/rvc/modules/vc/__init__.py b/rvc/modules/vc/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/rvc/modules/vc/modules.py b/rvc/modules/vc/modules.py
new file mode 100644
index 0000000000000000000000000000000000000000..ab499ed867fe1306d050a479be3498d2d8b18356
--- /dev/null
+++ b/rvc/modules/vc/modules.py
@@ -0,0 +1,250 @@
+import logging
+import traceback
+from collections import OrderedDict
+from io import BytesIO
+from pathlib import Path
+
+import numpy as np
+import soundfile as sf
+import torch
+
+from rvc.configs.config import Config
+from rvc.lib.audio import load_audio, wav2
+from rvc.lib.infer_pack.models import (
+    SynthesizerTrnMs256NSFsid,
+    SynthesizerTrnMs256NSFsid_nono,
+    SynthesizerTrnMs768NSFsid,
+    SynthesizerTrnMs768NSFsid_nono,
+)
+from rvc.modules.vc.pipeline import Pipeline
+from rvc.modules.vc.utils import *
+
+logger: logging.Logger = logging.getLogger(__name__)
+
+
+class VC:
+    def __init__(self):
+        self.n_spk: any = None
+        self.tgt_sr: int | None = None
+        self.net_g = None
+        self.pipeline: Pipeline | None = None
+        self.cpt: OrderedDict | None = None
+        self.version: str | None = None
+        self.if_f0: int | None = None
+        self.version: str | None = None
+        self.hubert_model: any = None
+
+        self.config = Config()
+
+    def get_vc(self, sid: str | Path, *to_return_protect: int):
+        logger.info("Get sid: " + os.path.basename(sid) if hasattr(sid, "name") or isinstance(sid, str) else "ERROR")
+
+        return_protect = [
+            to_return_protect[0] if self.if_f0 != 0 and to_return_protect else 0.5,
+            to_return_protect[1] if self.if_f0 != 0 and to_return_protect else 0.33,
+        ]
+
+        if hasattr(sid, "name"):
+            sid = sid.name
+        elif not isinstance(sid, str):
+            raise RuntimeError(f"pathlib.Path or str expected for sid. Got {type(sid)}")
+
+        weight_root = os.getenv("weight_root")
+        person = sid if os.path.exists(sid) else f'{weight_root if weight_root is not None else "."}/{sid}'
+        logger.info(f"Loading: {person}")
+        
+        if not os.path.exists(person) or person.endswith("/"):
+            raise FileNotFoundError(f"model file not found (path: {person}).")
+        
+        self.cpt = torch.load(person, weights_only=False, map_location="cpu")
+        self.tgt_sr = self.cpt["config"][-1]
+        self.cpt["config"][-3] = self.cpt["weight"]["emb_g.weight"].shape[0]  # n_spk
+        self.if_f0 = self.cpt.get("f0", 1)
+        self.version = self.cpt.get("version", "v1")
+
+        synthesizer_class = {
+            ("v1", 1): SynthesizerTrnMs256NSFsid,
+            ("v1", 0): SynthesizerTrnMs256NSFsid_nono,
+            ("v2", 1): SynthesizerTrnMs768NSFsid,
+            ("v2", 0): SynthesizerTrnMs768NSFsid_nono,
+        }
+
+        self.net_g = synthesizer_class.get(
+            (self.version, self.if_f0), SynthesizerTrnMs256NSFsid
+        )(*self.cpt["config"], is_half=self.config.is_half)
+
+        del self.net_g.enc_q
+
+        if len(sid) == 0:
+            logger.info("Clean model cache")
+            del (self.hubert_model, self.tgt_sr, self.net_g)
+            (self.net_g) = self.n_spk = index = None
+
+        else:
+            self.net_g.load_state_dict(self.cpt["weight"], strict=False)
+            self.net_g.eval().to(self.config.device)
+            self.net_g = (
+                self.net_g.half() if self.config.is_half else self.net_g.float()
+            )
+
+            self.pipeline = Pipeline(self.tgt_sr, self.config)
+            self.n_spk = self.cpt["config"][-3]
+            index = get_index_path_from_model(sid)
+            logger.info("Select index: " + index)
+
+        return self.n_spk, return_protect, index
+
+    def vc_inference(
+        self,
+        sid: int,
+        input_audio_path: Path | str,
+        f0_up_key: int = 0,
+        f0_method: str = "rmvpe",
+        f0_file: Path | str | None = None,
+        index_file: Path | str | None = None,
+        index_rate: float = 0.75,
+        filter_radius: int = 3,
+        resample_sr: int = 0,
+        rms_mix_rate: float = 0.25,
+        protect: float = 0.33,
+        hubert_path: str | Path | None = None,
+    ):
+        if hubert_path is None:
+            hubert_path = os.getenv("hubert_path")
+        elif hasattr(hubert_path, "name"):
+            hubert_path = hubert_path.name
+        elif not isinstance(hubert_path, str):
+            raise RuntimeError(f"pathlib.Path, str, or None expected for hubert_path. Got {type(hubert_path)}")
+        
+        if hubert_path is None or not os.path.exists(hubert_path):
+            raise FileNotFoundError("hubert_path not found.")
+
+        if hasattr(input_audio_path, "name"):
+            input_audio_path = input_audio_path.name
+        elif not isinstance(input_audio_path, str):
+            raise RuntimeError(f"pathlib.Path or str expected for input_audio_path. Got {type(input_audio_path)}")
+        
+        if not os.path.exists(input_audio_path):
+            raise FileNotFoundError("input_audio_path not found.")
+        
+        if isinstance(f0_file, str):
+            f0_file = Path(f0_file)
+        elif not isinstance(f0_file, Path) and f0_file is not None:
+            raise RuntimeError(f"pathlib.Path, str, or None expected for f0_file. Got {type(f0_file)}")
+        
+        if hasattr(f0_file, "name") and not os.path.exists(f0_file.name):
+            logger.warning("f0_file not found. Will use None instead.")
+            f0_file = None
+        
+        if hasattr(index_file, "name"):
+            index_file = index_file.name
+        elif not isinstance(index_file, str) and index_file is not None:
+            raise RuntimeError(f"pathlib.Path, str, or None expected for index_file. Got {type(index_file)}")
+        
+        if index_file is not None and not os.path.exists(index_file):
+            logger.warning("index_file not found. Will use None instead.")
+            index_file = None
+
+        try:
+            audio = load_audio(input_audio_path, 16000)
+            audio_max = np.abs(audio).max() / 0.95
+            if audio_max > 1:
+                audio /= audio_max
+            times = {"npy": 0, "f0": 0, "infer": 0}
+
+            if self.hubert_model is None:
+                self.hubert_model = load_hubert(self.config, hubert_path)
+
+            audio_opt = self.pipeline.pipeline(
+                self.hubert_model,
+                self.net_g,
+                sid,
+                audio,
+                input_audio_path,
+                times,
+                f0_up_key,
+                f0_method,
+                index_file,
+                index_rate,
+                self.if_f0,
+                filter_radius,
+                self.tgt_sr,
+                resample_sr,
+                rms_mix_rate,
+                self.version,
+                protect,
+                f0_file,
+            )
+
+            tgt_sr = resample_sr if self.tgt_sr != resample_sr >= 16000 else self.tgt_sr
+
+            return tgt_sr, audio_opt, times, None
+
+        except Exception:
+            info = traceback.format_exc()
+            logger.warning(info)
+            return None, None, None, info
+
+    def vc_multi(
+        self,
+        sid: int,
+        paths: list[Path | str],
+        opt_root: Path | str,
+        f0_up_key: int = 0,
+        f0_method: str = "rmvpe",
+        f0_file: Path | str | None = None,
+        index_file: Path | str | None = None,
+        index_rate: float = 0.75,
+        filter_radius: int = 3,
+        resample_sr: int = 0,
+        rms_mix_rate: float = 0.25,
+        protect: float = 0.33,
+        output_format: str = "wav",
+        hubert_path: str | Path | None = None,
+    ):
+        if hasattr(opt_root, "name"):
+            opt_root = opt_root.name
+
+        try:
+            os.makedirs(opt_root, exist_ok=True)
+            paths = [path.name if hasattr(path, "name") else path for path in paths]
+            infos = []
+            for path in paths:
+                tgt_sr, audio_opt, _, info = self.vc_inference(
+                    sid,
+                    path,
+                    f0_up_key,
+                    f0_method,
+                    f0_file,
+                    index_file,
+                    index_rate,
+                    filter_radius,
+                    resample_sr,
+                    rms_mix_rate,
+                    protect,
+                    hubert_path,
+                )
+                if info:
+                    try:
+                        if output_format in ["wav", "flac"]:
+                            sf.write(
+                                f"{opt_root}/{os.path.basename(path)}.{output_format}",
+                                audio_opt,
+                                tgt_sr,
+                            )
+                        else:
+                            with BytesIO() as wavf:
+                                sf.write(wavf, audio_opt, tgt_sr, format="wav")
+                                wavf.seek(0, 0)
+                                with open(
+                                    f"{opt_root}/{os.path.basename(path)}.{output_format}",
+                                    "wb",
+                                ) as outf:
+                                    wav2(wavf, outf, output_format)
+                    except Exception:
+                        info += traceback.format_exc()
+                infos.append(f"{os.path.basename(path)}->{info}")
+                yield "\n".join(infos)
+            yield "\n".join(infos)
+        except:
+            yield traceback.format_exc()
diff --git a/rvc/modules/vc/pipeline.py b/rvc/modules/vc/pipeline.py
new file mode 100644
index 0000000000000000000000000000000000000000..f859b6f66f5dee9b75fb7b9def751c22e718e0d3
--- /dev/null
+++ b/rvc/modules/vc/pipeline.py
@@ -0,0 +1,454 @@
+import logging
+import os
+import sys
+import traceback
+from functools import lru_cache
+from time import time as ttime
+
+import faiss
+import librosa
+import numpy as np
+import parselmouth
+import pyworld
+import torch
+import torch.nn.functional as F
+import torchcrepe
+from scipy import signal
+
+logger: logging.Logger = logging.getLogger(__name__)
+
+bh, ah = signal.butter(N=5, Wn=48, btype="high", fs=16000)
+
+input_audio_path2wav = {}
+
+
+@lru_cache
+def cache_harvest_f0(input_audio_path, fs, f0max, f0min, frame_period):
+    audio = input_audio_path2wav[input_audio_path]
+    f0, t = pyworld.harvest(
+        audio,
+        fs=fs,
+        f0_ceil=f0max,
+        f0_floor=f0min,
+        frame_period=frame_period,
+    )
+    f0 = pyworld.stonemask(audio, f0, t, fs)
+    return f0
+
+
+def change_rms(data1, sr1, data2, sr2, rate):  # 1是输入音频，2是输出音频,rate是2的占比
+    # print(data1.max(),data2.max())
+    rms1 = librosa.feature.rms(
+        y=data1, frame_length=sr1 // 2 * 2, hop_length=sr1 // 2
+    )  # 每半秒一个点
+    rms2 = librosa.feature.rms(y=data2, frame_length=sr2 // 2 * 2, hop_length=sr2 // 2)
+    rms1 = torch.from_numpy(rms1)
+    rms1 = F.interpolate(
+        rms1.unsqueeze(0), size=data2.shape[0], mode="linear"
+    ).squeeze()
+    rms2 = torch.from_numpy(rms2)
+    rms2 = F.interpolate(
+        rms2.unsqueeze(0), size=data2.shape[0], mode="linear"
+    ).squeeze()
+    rms2 = torch.max(rms2, torch.zeros_like(rms2) + 1e-6)
+    data2 *= (
+        torch.pow(rms1, torch.tensor(1 - rate))
+        * torch.pow(rms2, torch.tensor(rate - 1))
+    ).numpy()
+    return data2
+
+
+class Pipeline(object):
+    def __init__(self, tgt_sr, config):
+        self.x_pad, self.x_query, self.x_center, self.x_max, self.is_half = (
+            config.x_pad,
+            config.x_query,
+            config.x_center,
+            config.x_max,
+            config.is_half,
+        )
+        self.sr = 16000  # hubert输入采样率
+        self.window = 160  # 每帧点数
+        self.t_pad = self.sr * self.x_pad  # 每条前后pad时间
+        self.t_pad_tgt = tgt_sr * self.x_pad
+        self.t_pad2 = self.t_pad * 2
+        self.t_query = self.sr * self.x_query  # 查询切点前后查询时间
+        self.t_center = self.sr * self.x_center  # 查询切点位置
+        self.t_max = self.sr * self.x_max  # 免查询时长阈值
+        self.device = config.device
+
+    def get_f0(
+        self,
+        input_audio_path,
+        x,
+        p_len,
+        f0_up_key,
+        f0_method,
+        filter_radius,
+        inp_f0=None,
+    ):
+        global input_audio_path2wav
+        time_step = self.window / self.sr * 1000
+        f0_min = 50
+        f0_max = 1100
+        f0_mel_min = 1127 * np.log(1 + f0_min / 700)
+        f0_mel_max = 1127 * np.log(1 + f0_max / 700)
+        if f0_method == "pm":
+            f0 = (
+                parselmouth.Sound(x, self.sr)
+                .to_pitch_ac(
+                    time_step=time_step / 1000,
+                    voicing_threshold=0.6,
+                    pitch_floor=f0_min,
+                    pitch_ceiling=f0_max,
+                )
+                .selected_array["frequency"]
+            )
+            pad_size = (p_len - len(f0) + 1) // 2
+            if pad_size > 0 or p_len - len(f0) - pad_size > 0:
+                f0 = np.pad(
+                    f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant"
+                )
+        elif f0_method == "harvest":
+            input_audio_path2wav[input_audio_path] = x.astype(np.double)
+            f0 = cache_harvest_f0(input_audio_path, self.sr, f0_max, f0_min, 10)
+            if filter_radius > 2:
+                f0 = signal.medfilt(f0, 3)
+        elif f0_method == "crepe":
+            model = "full"
+            # Pick a batch size that doesn't cause memory errors on your gpu
+            batch_size = 512
+            # Compute pitch using first gpu
+            audio = torch.tensor(np.copy(x))[None].float()
+            f0, pd = torchcrepe.predict(
+                audio,
+                self.sr,
+                self.window,
+                f0_min,
+                f0_max,
+                model,
+                batch_size=batch_size,
+                device=self.device,
+                return_periodicity=True,
+            )
+            pd = torchcrepe.filter.median(pd, 3)
+            f0 = torchcrepe.filter.mean(f0, 3)
+            f0[pd < 0.1] = 0
+            f0 = f0[0].cpu().numpy()
+        elif f0_method == "rmvpe":
+            if not hasattr(self, "model_rmvpe"):
+                from rvc.lib.rmvpe import RMVPE
+
+                logger.info(
+                    "Loading rmvpe model,%s" % "%s/rmvpe.pt" % os.environ["rmvpe_root"]
+                )
+                self.model_rmvpe = RMVPE(
+                    "%s/rmvpe.pt" % os.environ["rmvpe_root"],
+                    is_half=self.is_half,
+                    device=self.device,
+                )
+            f0 = self.model_rmvpe.infer_from_audio(x, thred=0.03)
+
+            if "privateuseone" in str(self.device):  # clean ortruntime memory
+                del self.model_rmvpe.model
+                del self.model_rmvpe
+                logger.info("Cleaning ortruntime memory")
+
+        f0 *= pow(2, f0_up_key / 12)
+        # with open("test.txt","w")as f:f.write("\n".join([str(i)for i in f0.tolist()]))
+        tf0 = self.sr // self.window  # 每秒f0点数
+        if inp_f0 is not None:
+            delta_t = np.round(
+                (inp_f0[:, 0].max() - inp_f0[:, 0].min()) * tf0 + 1
+            ).astype("int16")
+            replace_f0 = np.interp(
+                list(range(delta_t)), inp_f0[:, 0] * 100, inp_f0[:, 1]
+            )
+            shape = f0[self.x_pad * tf0 : self.x_pad * tf0 + len(replace_f0)].shape[0]
+            f0[self.x_pad * tf0 : self.x_pad * tf0 + len(replace_f0)] = replace_f0[
+                :shape
+            ]
+        # with open("test_opt.txt","w")as f:f.write("\n".join([str(i)for i in f0.tolist()]))
+        f0bak = f0.copy()
+        f0_mel = 1127 * np.log(1 + f0 / 700)
+        f0_mel[f0_mel > 0] = (f0_mel[f0_mel > 0] - f0_mel_min) * 254 / (
+            f0_mel_max - f0_mel_min
+        ) + 1
+        f0_mel[f0_mel <= 1] = 1
+        f0_mel[f0_mel > 255] = 255
+        f0_coarse = np.rint(f0_mel).astype(np.int32)
+        return f0_coarse, f0bak  # 1-0
+
+    def vc(
+        self,
+        model,
+        net_g,
+        sid,
+        audio0,
+        pitch,
+        pitchf,
+        times,
+        index,
+        big_npy,
+        index_rate,
+        version,
+        protect,
+    ):  # ,file_index,file_big_npy
+        feats = torch.from_numpy(audio0)
+        if self.is_half:
+            feats = feats.half()
+        else:
+            feats = feats.float()
+        if feats.dim() == 2:  # double channels
+            feats = feats.mean(-1)
+        assert feats.dim() == 1, feats.dim()
+        feats = feats.view(1, -1)
+        padding_mask = torch.BoolTensor(feats.shape).to(self.device).fill_(False)
+
+        inputs = {
+            "source": feats.to(self.device),
+            "padding_mask": padding_mask,
+            "output_layer": 9 if version == "v1" else 12,
+        }
+        t0 = ttime()
+        with torch.no_grad():
+            logits = model.extract_features(**inputs)
+            feats = model.final_proj(logits[0]) if version == "v1" else logits[0]
+        if protect < 0.5 and pitch is not None and pitchf is not None:
+            feats0 = feats.clone()
+        if (
+            not isinstance(index, type(None))
+            and not isinstance(big_npy, type(None))
+            and index_rate != 0
+        ):
+            npy = feats[0].cpu().numpy()
+            if self.is_half:
+                npy = npy.astype("float32")
+
+            # _, I = index.search(npy, 1)
+            # npy = big_npy[I.squeeze()]
+
+            score, ix = index.search(npy, k=8)
+            weight = np.square(1 / score)
+            weight /= weight.sum(axis=1, keepdims=True)
+            npy = np.sum(big_npy[ix] * np.expand_dims(weight, axis=2), axis=1)
+
+            if self.is_half:
+                npy = npy.astype("float16")
+            feats = (
+                torch.from_numpy(npy).unsqueeze(0).to(self.device) * index_rate
+                + (1 - index_rate) * feats
+            )
+
+        feats = F.interpolate(feats.permute(0, 2, 1), scale_factor=2).permute(0, 2, 1)
+        if protect < 0.5 and pitch is not None and pitchf is not None:
+            feats0 = F.interpolate(feats0.permute(0, 2, 1), scale_factor=2).permute(
+                0, 2, 1
+            )
+        t1 = ttime()
+        p_len = audio0.shape[0] // self.window
+        if feats.shape[1] < p_len:
+            p_len = feats.shape[1]
+            if pitch is not None and pitchf is not None:
+                pitch = pitch[:, :p_len]
+                pitchf = pitchf[:, :p_len]
+
+        if protect < 0.5 and pitch is not None and pitchf is not None:
+            pitchff = pitchf.clone()
+            pitchff[pitchf > 0] = 1
+            pitchff[pitchf < 1] = protect
+            pitchff = pitchff.unsqueeze(-1)
+            feats = feats * pitchff + feats0 * (1 - pitchff)
+            feats = feats.to(feats0.dtype)
+        p_len = torch.tensor([p_len], device=self.device).long()
+        with torch.no_grad():
+            hasp = pitch is not None and pitchf is not None
+            arg = (feats, p_len, pitch, pitchf, sid) if hasp else (feats, p_len, sid)
+            audio1 = (net_g.infer(*arg)[0][0, 0]).data.cpu().float().numpy()
+            del hasp, arg
+        del feats, p_len, padding_mask
+        if torch.cuda.is_available():
+            torch.cuda.empty_cache()
+        t2 = ttime()
+        times["npy"] += t1 - t0
+        times["infer"] += t2 - t1
+        return audio1
+
+    def pipeline(
+        self,
+        model,
+        net_g,
+        sid,
+        audio,
+        input_audio_path,
+        times,
+        f0_up_key,
+        f0_method,
+        file_index,
+        index_rate,
+        if_f0,
+        filter_radius,
+        tgt_sr,
+        resample_sr,
+        rms_mix_rate,
+        version,
+        protect,
+        f0_file=None,
+    ):
+        if (
+            file_index
+            and file_index != ""
+            # and file_big_npy != ""
+            # and os.path.exists(file_big_npy) == True
+            and os.path.exists(file_index)
+            and index_rate != 0
+        ):
+            try:
+                index = faiss.read_index(file_index)
+                # big_npy = np.load(file_big_npy)
+                big_npy = index.reconstruct_n(0, index.ntotal)
+            except:
+                traceback.print_exc()
+                index = big_npy = None
+        else:
+            index = big_npy = None
+        audio = signal.filtfilt(bh, ah, audio)
+        audio_pad = np.pad(audio, (self.window // 2, self.window // 2), mode="reflect")
+        opt_ts = []
+        if audio_pad.shape[0] > self.t_max:
+            audio_sum = np.zeros_like(audio)
+            for i in range(self.window):
+                audio_sum += np.abs(audio_pad[i : i - self.window])
+            for t in range(self.t_center, audio.shape[0], self.t_center):
+                opt_ts.append(
+                    t
+                    - self.t_query
+                    + np.where(
+                        audio_sum[t - self.t_query : t + self.t_query]
+                        == audio_sum[t - self.t_query : t + self.t_query].min()
+                    )[0][0]
+                )
+        s = 0
+        audio_opt = []
+        t = None
+        t1 = ttime()
+        audio_pad = np.pad(audio, (self.t_pad, self.t_pad), mode="reflect")
+        p_len = audio_pad.shape[0] // self.window
+        inp_f0 = None
+        if hasattr(f0_file, "name"):
+            try:
+                with open(f0_file.name, "r") as f:
+                    lines = f.read().strip("\n").split("\n")
+                inp_f0 = []
+                for line in lines:
+                    inp_f0.append([float(i) for i in line.split(",")])
+                inp_f0 = np.array(inp_f0, dtype="float32")
+            except:
+                traceback.print_exc()
+        sid = torch.tensor(sid, device=self.device).unsqueeze(0).long()
+        pitch, pitchf = None, None
+        if if_f0 == 1:
+            pitch, pitchf = self.get_f0(
+                input_audio_path,
+                audio_pad,
+                p_len,
+                f0_up_key,
+                f0_method,
+                filter_radius,
+                inp_f0,
+            )
+            pitch = pitch[:p_len]
+            pitchf = pitchf[:p_len]
+            if "mps" not in str(self.device) or "xpu" not in str(self.device):
+                pitchf = pitchf.astype(np.float32)
+            pitch = torch.tensor(pitch, device=self.device).unsqueeze(0).long()
+            pitchf = torch.tensor(pitchf, device=self.device).unsqueeze(0).float()
+        t2 = ttime()
+        times["f0"] += t2 - t1
+        for t in opt_ts:
+            t = t // self.window * self.window
+            if if_f0 == 1:
+                audio_opt.append(
+                    self.vc(
+                        model,
+                        net_g,
+                        sid,
+                        audio_pad[s : t + self.t_pad2 + self.window],
+                        pitch[:, s // self.window : (t + self.t_pad2) // self.window],
+                        pitchf[:, s // self.window : (t + self.t_pad2) // self.window],
+                        times,
+                        index,
+                        big_npy,
+                        index_rate,
+                        version,
+                        protect,
+                    )[self.t_pad_tgt : -self.t_pad_tgt]
+                )
+            else:
+                audio_opt.append(
+                    self.vc(
+                        model,
+                        net_g,
+                        sid,
+                        audio_pad[s : t + self.t_pad2 + self.window],
+                        None,
+                        None,
+                        times,
+                        index,
+                        big_npy,
+                        index_rate,
+                        version,
+                        protect,
+                    )[self.t_pad_tgt : -self.t_pad_tgt]
+                )
+            s = t
+        if if_f0 == 1:
+            audio_opt.append(
+                self.vc(
+                    model,
+                    net_g,
+                    sid,
+                    audio_pad[t:],
+                    pitch[:, t // self.window :] if t is not None else pitch,
+                    pitchf[:, t // self.window :] if t is not None else pitchf,
+                    times,
+                    index,
+                    big_npy,
+                    index_rate,
+                    version,
+                    protect,
+                )[self.t_pad_tgt : -self.t_pad_tgt]
+            )
+        else:
+            audio_opt.append(
+                self.vc(
+                    model,
+                    net_g,
+                    sid,
+                    audio_pad[t:],
+                    None,
+                    None,
+                    times,
+                    index,
+                    big_npy,
+                    index_rate,
+                    version,
+                    protect,
+                )[self.t_pad_tgt : -self.t_pad_tgt]
+            )
+        audio_opt = np.concatenate(audio_opt)
+        if rms_mix_rate != 1:
+            audio_opt = change_rms(audio, 16000, audio_opt, tgt_sr, rms_mix_rate)
+        if tgt_sr != resample_sr >= 16000:
+            audio_opt = librosa.resample(
+                audio_opt, orig_sr=tgt_sr, target_sr=resample_sr
+            )
+        audio_max = np.abs(audio_opt).max() / 0.99
+        max_int16 = 32768
+        if audio_max > 1:
+            max_int16 /= audio_max
+        audio_opt = (audio_opt * max_int16).astype(np.int16)
+        del pitch, pitchf, sid
+        if torch.cuda.is_available():
+            torch.cuda.empty_cache()
+        return audio_opt
diff --git a/rvc/modules/vc/utils.py b/rvc/modules/vc/utils.py
new file mode 100644
index 0000000000000000000000000000000000000000..47c590e27cad4152b989c264e58f34e39343a3b3
--- /dev/null
+++ b/rvc/modules/vc/utils.py
@@ -0,0 +1,30 @@
+import os
+
+from fairseq import checkpoint_utils
+
+
+def get_index_path_from_model(sid):
+    return next(
+        (
+            f
+            for f in [
+                os.path.join(root, name)
+                for root, _, files in os.walk(os.getenv("index_root"), topdown=False)
+                for name in files
+                if name.endswith(".index") and "trained" not in name
+            ]
+            if str(sid).split(".")[0] in f
+        ),
+        "",
+    )
+
+
+def load_hubert(config, hubert_path: str):
+    models, _, _ = checkpoint_utils.load_model_ensemble_and_task(
+        [hubert_path],
+        suffix="",
+    )
+    hubert_model = models[0]
+    hubert_model = hubert_model.to(config.device)
+    hubert_model = hubert_model.half() if config.is_half else hubert_model.float()
+    return hubert_model.eval()
diff --git a/rvc/wrapper/api/api.py b/rvc/wrapper/api/api.py
new file mode 100644
index 0000000000000000000000000000000000000000..faba78dac727312ca942709e50f2d0fb0c9b16c1
--- /dev/null
+++ b/rvc/wrapper/api/api.py
@@ -0,0 +1,11 @@
+import uvicorn
+from dotenv import load_dotenv
+from fastapi import FastAPI
+
+from rvc.wrapper.api.endpoints import inference
+
+load_dotenv()
+
+app = FastAPI()
+
+app.include_router(inference.router)
diff --git a/rvc/wrapper/api/endpoints/inference.py b/rvc/wrapper/api/endpoints/inference.py
new file mode 100644
index 0000000000000000000000000000000000000000..8ae0135eaca47283c191677c3c432972c8e2c5dc
--- /dev/null
+++ b/rvc/wrapper/api/endpoints/inference.py
@@ -0,0 +1,76 @@
+import json
+from io import BytesIO
+from pathlib import Path
+
+from fastapi import APIRouter, Response, UploadFile, Body, responses, Form, Query
+from fastapi.responses import JSONResponse
+
+from pydantic import BaseModel
+from scipy.io import wavfile
+from base64 import b64encode
+from rvc.modules.vc.modules import VC
+import glob
+import os
+
+router = APIRouter()
+from dotenv import load_dotenv
+
+load_dotenv()
+
+
+@router.post("/inference")
+def inference(
+    input_audio: Path | UploadFile,
+    modelpath: Path
+    | UploadFile = Body(
+        ...,
+        enum=[
+            os.path.basename(file)
+            for file in glob.glob(f"{os.getenv('weight_root')}/*")
+        ],
+    ),
+    res_type: str = Query("blob", enum=["blob", "json"]),
+    sid: int = 0,
+    f0_up_key: int = 0,
+    f0_method: str = Query(
+        "rmvpe", enum=["pm", "harvest", "dio", "rmvpe", "rmvpe_gpu"]
+    ),
+    f0_file: Path | None = None,
+    index_file: Path | None = None,
+    index_rate: float = 0.75,
+    filter_radius: int = 3,
+    resample_sr: int = 0,
+    rms_mix_rate: float = 0.25,
+    protect: float = 0.33,
+):
+    print(res_type)
+    vc = VC()
+    vc.get_vc(modelpath)
+    tgt_sr, audio_opt, times, _ = vc.vc_inference(
+        sid,
+        input_audio,
+        f0_up_key,
+        f0_method,
+        f0_file,
+        index_file,
+        index_rate,
+        filter_radius,
+        resample_sr,
+        rms_mix_rate,
+        protect,
+    )
+    wavfile.write(wv := BytesIO(), tgt_sr, audio_opt)
+    print(times)
+    if res_type == "blob":
+        return responses.StreamingResponse(
+            wv,
+            media_type="audio/wav",
+            headers={"Content-Disposition": "attachment; filename=inference.wav"},
+        )
+    else:
+        return JSONResponse(
+            {
+                "time": json.loads(json.dumps(times)),
+                "audio": b64encode(wv.read()).decode("utf-8"),
+            }
+        )
diff --git a/rvc/wrapper/api/endpoints/uvr.py b/rvc/wrapper/api/endpoints/uvr.py
new file mode 100644
index 0000000000000000000000000000000000000000..58faddd8cddb3ee7717fa7cf107fd70538a314cd
--- /dev/null
+++ b/rvc/wrapper/api/endpoints/uvr.py
@@ -0,0 +1,18 @@
+from fastapi import APIRouter, Response, UploadFile, responses
+
+from rvc.modules.uvr5.modules import UVR
+
+router = APIRouter()
+
+
+@router.post("/inference")
+def uvr(inputpath, outputpath, modelname, format):
+    uvr_module = UVR()
+    uvr_module.uvr_wrapper(
+        inputpath, outputpath, model_name=modelname, export_format=format
+    )
+    return responses.StreamingResponse(
+        audio,
+        media_type="audio/wav",
+        headers={"Content-Disposition": "attachment; filename=inference.wav"},
+    )
diff --git a/rvc/wrapper/cli/cli.py b/rvc/wrapper/cli/cli.py
new file mode 100644
index 0000000000000000000000000000000000000000..547046339116a78653d8328fff25f9f8931af758
--- /dev/null
+++ b/rvc/wrapper/cli/cli.py
@@ -0,0 +1,33 @@
+import re
+from typing import Optional, Pattern
+
+import click
+
+from rvc.wrapper.cli.handler.infer import infer
+from rvc.wrapper.cli.handler.train import train
+from rvc.wrapper.cli.handler.uvr5 import uvr
+from rvc.wrapper.cli.utils.dlmodel import dlmodel
+from rvc.wrapper.cli.utils.env import env
+from rvc.wrapper.cli.utils.initialize import init
+
+
+@click.group(
+    context_settings={"help_option_names": ["-h", "--help"]},
+    help="rvc cli feature list",
+)
+def cli():
+    pass
+
+
+def main():
+    cli.add_command(infer)
+    cli.add_command(train)
+    cli.add_command(uvr)
+    cli.add_command(dlmodel)
+    cli.add_command(env)
+    cli.add_command(init)
+    cli()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/rvc/wrapper/cli/handler/infer.py b/rvc/wrapper/cli/handler/infer.py
new file mode 100644
index 0000000000000000000000000000000000000000..872cdc99c8d277e13cea74498eac947f93e95703
--- /dev/null
+++ b/rvc/wrapper/cli/handler/infer.py
@@ -0,0 +1,132 @@
+import logging
+from pathlib import Path
+
+import click
+from dotenv import load_dotenv
+from scipy.io import wavfile
+
+logging.getLogger("numba").setLevel(logging.WARNING)
+
+
+@click.command(
+    context_settings={"help_option_names": ["-h", "--help"]},
+    help="inference audio",
+)
+@click.option(
+    "-m",
+    "--modelPath",
+    is_flag=False,
+    type=str,
+    help="Model path or filename (reads in the directory set in env)",
+    required=True,
+)
+@click.option(
+    "-i",
+    "--inputPath",
+    is_flag=False,
+    type=Path,
+    help="input audio path or folder",
+    required=True,
+)
+@click.option(
+    "-o",
+    "--outputPath",
+    is_flag=False,
+    type=Path,
+    help="output audio path or folder",
+    required=True,
+)
+@click.option(
+    "-s", "--sid", is_flag=False, type=int, help="Speaker/Singer id", default=0
+)
+@click.option("-fu", "--f0upkey", is_flag=False, type=int, help="Transpose", default=0)
+@click.option(
+    "-fm",
+    "--f0method",
+    is_flag=False,
+    type=str,
+    help="Pitch extraction algorith",
+    default="rmvpe",
+)
+@click.option(
+    "-ff", "--f0file", is_flag=False, type=Path, help="F0 curve file (optional)"
+)
+@click.option("-if", "--indexFile", is_flag=False, type=Path, help="Feature index file")
+@click.option(
+    "-ir",
+    "--indexRate",
+    is_flag=False,
+    type=float,
+    help="Search feature ratio",
+    default=0.75,
+)
+@click.option(
+    "-fr",
+    "--filterRadius",
+    is_flag=False,
+    type=int,
+    help="Apply median filtering",
+    default=3,
+)
+@click.option(
+    "-rsr",
+    "--resamplesr",
+    is_flag=False,
+    type=int,
+    help="Resample the output audio",
+    default=0,
+)
+@click.option(
+    "-rmr",
+    "--rmsmixrate",
+    is_flag=False,
+    type=float,
+    help="Adjust the volume envelope scaling",
+    default=0.25,
+)
+@click.option(
+    "-p",
+    "--protect",
+    is_flag=False,
+    type=float,
+    help="Protect voiceless consonants and breath sounds",
+    default=0.33,
+)
+def infer(
+    modelpath,
+    inputpath,
+    outputpath,
+    sid,
+    f0upkey,
+    f0method,
+    f0file,
+    indexfile,
+    indexrate,
+    filterradius,
+    resamplesr,
+    rmsmixrate,
+    protect,
+):
+    from rvc.modules.vc.modules import VC
+
+    load_dotenv()
+    vc = VC()
+    vc.get_vc(modelpath)
+    tgt_sr, audio_opt, times, _ = vc.vc_inference(
+        sid,
+        inputpath,
+        f0upkey,
+        f0method,
+        f0file,
+        indexfile,
+        indexrate,
+        filterradius,
+        resamplesr,
+        rmsmixrate,
+        protect,
+    )
+    if outputpath:
+        wavfile.write(outputpath, tgt_sr, audio_opt)
+        click.echo(times)
+        click.echo(f"Finish inference. Check {outputpath}")
+    return tgt_sr, audio_opt, times
diff --git a/rvc/wrapper/cli/handler/train.py b/rvc/wrapper/cli/handler/train.py
new file mode 100644
index 0000000000000000000000000000000000000000..d5ff831e4bf61db3e2ed13b3fadfdd1fe395e614
--- /dev/null
+++ b/rvc/wrapper/cli/handler/train.py
@@ -0,0 +1,6 @@
+import click
+
+
+@click.command()
+def train():
+    pass
diff --git a/rvc/wrapper/cli/handler/uvr5.py b/rvc/wrapper/cli/handler/uvr5.py
new file mode 100644
index 0000000000000000000000000000000000000000..06efb5b799ed542fca85f2719a01a236376f8add
--- /dev/null
+++ b/rvc/wrapper/cli/handler/uvr5.py
@@ -0,0 +1,45 @@
+from pathlib import Path
+
+import click
+
+from rvc.modules.uvr5.modules import UVR
+
+
+@click.command()
+@click.option(
+    "-m",
+    "--modelName",
+    is_flag=False,
+    type=str,
+    help="Model path or filename (reads in the directory set in env)",
+    # required=True,
+)
+@click.option(
+    "-i",
+    "--inputPath",
+    is_flag=False,
+    type=Path,
+    help="input audio path or folder",
+    # required=True,
+)
+@click.option(
+    "-o",
+    "--outputPath",
+    is_flag=False,
+    type=Path,
+    help="output audio path or folder",
+    required=True,
+)
+@click.option(
+    "-f",
+    "--format",
+    is_flag=False,
+    type=str,
+    help="output Format",
+)
+def uvr(modelname, inputpath, outputpath, format):
+    uvr_module = UVR()
+    uvr_module.uvr_wrapper(
+        inputpath, outputpath, model_name=modelname, export_format=format
+    )
+    click.echo(f"Finish uvr5. Check {outputpath}")
diff --git a/rvc/wrapper/cli/utils/dlmodel.py b/rvc/wrapper/cli/utils/dlmodel.py
new file mode 100644
index 0000000000000000000000000000000000000000..632264819f18138b247f9e8e19b2aa2929fca8f6
--- /dev/null
+++ b/rvc/wrapper/cli/utils/dlmodel.py
@@ -0,0 +1,9 @@
+import urllib
+
+import click
+
+
+@click.command()
+def dlmodel() -> None:
+    # Download models [harvest, uvr5, and more ]
+    pass
diff --git a/rvc/wrapper/cli/utils/env.py b/rvc/wrapper/cli/utils/env.py
new file mode 100644
index 0000000000000000000000000000000000000000..0393dd46904e7928625a91bcab6f0a44b6f4bbc0
--- /dev/null
+++ b/rvc/wrapper/cli/utils/env.py
@@ -0,0 +1,40 @@
+"""
+setup or cleanup enviroment file
+usage: rvc env [create / cleanup]
+Default: [nowDir/.env]
+
+"""
+
+import os
+
+import click
+
+
+@click.group()
+def env():
+    pass
+
+
+@env.command()
+def create():
+    env_file_path = os.path.join(os.getcwd(), ".env")
+
+    if not os.path.exists(env_file_path):
+        default_values = {
+            "weight_root": "",
+            "weight_uvr5_root": "",
+            "index_root": "",
+            "rmvpe_root": "",
+            "hubert_path": "",
+            "save_uvr_path": "",
+            "TEMP": "",
+            "pretrained": "",
+        }
+
+        with open(env_file_path, "w") as env_file:
+            for key, value in default_values.items():
+                env_file.write(f"{key}={value}\n")
+
+        click.echo(f"{env_file_path} created successfully.")
+    else:
+        click.echo(f"{env_file_path} already exists, no change")
diff --git a/rvc/wrapper/cli/utils/initialize.py b/rvc/wrapper/cli/utils/initialize.py
new file mode 100644
index 0000000000000000000000000000000000000000..eda931c7e904134b16088ed30014511fa8b9a4c0
--- /dev/null
+++ b/rvc/wrapper/cli/utils/initialize.py
@@ -0,0 +1,11 @@
+"""
+Uage: rvc init
+download model and setup environmmnt file
+
+"""
+import click
+
+
+@click.command()
+def init():
+    pass