|
|
--- |
|
|
license: cc0-1.0 |
|
|
language: |
|
|
- az |
|
|
base_model: |
|
|
- ResembleAI/chatterbox |
|
|
pipeline_tag: text-to-speech |
|
|
library_name: transformers |
|
|
tags: |
|
|
- azerbaijani |
|
|
- Azerbaijan |
|
|
- voice-cloning |
|
|
- TTS |
|
|
--- |
|
|
|
|
|
# Chatterbox Azerbaijani |
|
|
## **Training quality TTS with limited data.** |
|
|
|
|
|
<div align="center"><img width="400px" src="https://www.shutterstock.com/image-vector/baku-azerbaijan-august-5-2024-600nw-2498859909.jpg" alt="Azerbaijani-image" /></div> |
|
|
|
|
|
### demo audios: |
|
|
|
|
|
"Salam, sən necəsən? Mən yaxşıyam, təşəkkür edirəm" |
|
|
<audio controls src="https://huggingface.co/Thomcles/Chatterbox-TTS-French/resolve/main/demo_audios/az_0.mp3">Your browser does not support audio.</audio> |
|
|
|
|
|
"Bu gün havalar çox isti və günəşlidir." |
|
|
<audio controls src="https://huggingface.co/Thomcles/Chatterbox-TTS-French/resolve/main/demo_audios/az_1.mp3">Your browser does not support audio.</audio> |
|
|
|
|
|
"Bakı Azərbaycanın paytaxtıdır və çox gözəldir." |
|
|
<audio controls src="https://huggingface.co/Thomcles/Chatterbox-TTS-French/resolve/main/demo_audios/az_2.mp3">Your browser does not support audio.</audio> |
|
|
|
|
|
"Mən azərbaycan dilini sevirəm və onu öyrənmək istəyirəm." |
|
|
<audio controls src="https://huggingface.co/Thomcles/Chatterbox-TTS-French/resolve/main/demo_audios/az_3.mp3">Your browser does not support audio.</audio> |
|
|
|
|
|
"Dünən dostumla birlikdə kinoya getdik və çox xoşbəxt idik." |
|
|
<audio controls src="https://huggingface.co/Thomcles/Chatterbox-TTS-French/resolve/main/demo_audios/az_4.mp3">Your browser does not support audio.</audio> |
|
|
|
|
|
|
|
|
### 💻 Inference Code |
|
|
|
|
|
First, download the file from huggingface and place it in the current directory. |
|
|
|
|
|
The pypi version is delayed, so you must use the github version. |
|
|
|
|
|
``` |
|
|
!git clone https://github.com/resemble-ai/chatterbox.git chatterbox_git |
|
|
``` |
|
|
|
|
|
``` |
|
|
!pip install chatterbox-tts |
|
|
``` |
|
|
|
|
|
```python |
|
|
from chatterbox_git.src.chatterbox import mtl_tts |
|
|
import torchaudio as ta |
|
|
from safetensors.torch import load_file as load_safetensors |
|
|
|
|
|
device = "cpu" # or mps or cuda |
|
|
|
|
|
multilingual_model = mtl_tts.ChatterboxMultilingualTTS.from_pretrained(device=device) |
|
|
|
|
|
# ---- |
|
|
# Then download the file from huggingface and place it in the current directory. |
|
|
# ---- |
|
|
|
|
|
|
|
|
|
|
|
t3_state = load_safetensors("t3_az.safetensors", device="cpu") |
|
|
multilingual_model.t3.load_state_dict(t3_state) |
|
|
multilingual_model.t3.to(device).eval() |
|
|
|
|
|
azerbaijani_text = "Dünən dostumla birlikdə kinoya getdik və çox xoşbəxt idik" |
|
|
wav_azerbaijani = multilingual_model.generate(azerbaijani_text) |
|
|
ta.save("test-az.wav", wav_azerbaijani, multilingual_model.sr) |
|
|
``` |
|
|
|
|
|
## contact : |
|
|
e-mail : [email protected] |
|
|
|
|
|
## ☕ Support |
|
|
|
|
|
I trained this model from my own financial resources with the sole aim of offering it to the huggingface open source community. |
|
|
|
|
|
This model has cost me a lot of money. If you find this checkpoint useful and would like to support my work, you can do it via Ko-fi: |
|
|
|
|
|
<p align="center"> |
|
|
<a href="https://ko-fi.com/thomcles" target="_blank" rel="noopener noreferrer"> |
|
|
<img src="https://storage.ko-fi.com/cdn/kofi3.png?v=3" alt="Buy Me a Coffee at ko-fi.com" width="200" rel="noopener noreferrer"/> |
|
|
</a> |
|
|
</p> |
|
|
|
|
|
## LIMITED OFFER: |
|
|
|
|
|
<p align="center"> |
|
|
Get a TTS in your language for $20+ |
|
|
3 slots left : |
|
|
<a href="https://ko-fi.com/c/74b39d650f" target="_blank" rel="noopener noreferrer"> |
|
|
<img src="https://storage.ko-fi.com/cdn/kofi3.png?v=3" alt="Request a custom TTS model" width="200" rel="noopener noreferrer"/> |
|
|
</a> |
|
|
</p> |
