Duplicate from FireRedTeam/FireRedTTS2

Co-authored-by: FireRedTeam <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Qwen2.5-1.5B/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Qwen2.5-1.5B/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2024 Alibaba Cloud
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

Qwen2.5-1.5B/README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen2.5-1.5B/blob/main/LICENSE
+language:
+- en
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# Qwen2.5-1.5B
+
+## Introduction
+
+Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:
+
+- Significantly **more knowledge** and has greatly improved capabilities in **coding** and **mathematics**, thanks to our specialized expert models in these domains.
+- Significant improvements in **instruction following**, **generating long texts** (over 8K tokens), **understanding structured data** (e.g, tables), and **generating structured outputs** especially JSON. **More resilient to the diversity of system prompts**, enhancing role-play implementation and condition-setting for chatbots.
+- **Long-context Support** up to 128K tokens and can generate up to 8K tokens.
+- **Multilingual support** for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. 
+
+**This repo contains the base 1.5B Qwen2.5 model**, which has the following features:
+- Type: Causal Language Models
+- Training Stage: Pretraining
+- Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
+- Number of Parameters: 1.54B
+- Number of Paramaters (Non-Embedding): 1.31B
+- Number of Layers: 28
+- Number of Attention Heads (GQA): 12 for Q and 2 for KV
+- Context Length: Full 32,768 tokens
+
+**We do not recommend using base language models for conversations.** Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., on this model.
+
+For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/).
+
+## Requirements
+
+The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
+
+With `transformers<4.37.0`, you will encounter the following error:
+```
+KeyError: 'qwen2'
+```
+
+## Evaluation & Performance
+
+Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5/).
+
+For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html).
+
+## Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+```
+@misc{qwen2.5,
+    title = {Qwen2.5: A Party of Foundation Models},
+    url = {https://qwenlm.github.io/blog/qwen2.5/},
+    author = {Qwen Team},
+    month = {September},
+    year = {2024}
+}
+
+@article{qwen2,
+      title={Qwen2 Technical Report}, 
+      author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
+      journal={arXiv preprint arXiv:2407.10671},
+      year={2024}
+}
+```

Qwen2.5-1.5B/config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

Qwen2.5-1.5B/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": false,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.37.0"
+}

Qwen2.5-1.5B/original_repo_id.json

@@ -0,0 +1,3 @@
+{
+    "repo_id": "Qwen/Qwen2.5-1.5B"
+}

Qwen2.5-1.5B/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

README.md

@@ -0,0 +1,189 @@
+---
+license: apache-2.0
+---
+<div align="center">
+    <h1>
+    FireRedTTS-2
+    </h1>
+    <p>
+    Official PyTorch code for <br>
+    <b><em>FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot</em></b>
+    </p>
+    <a href="https://arxiv.org/abs/2509.02020"><img src="https://img.shields.io/badge/Paper-ArXiv-red" alt="technical report"></a>
+    <a href="https://fireredteam.github.io/demos/firered_tts_2/"><img src="https://img.shields.io/badge/Demo-Page-lightgrey" alt="version"></a>
+    <a href="https://huggingface.co/FireRedTeam/FireRedTTS2"><img src="https://img.shields.io/badge/Hugging%20Face-Model%20Page-yellow" alt="HF-model"></a>
+    <a href="https://github.com/FireRedTeam/FireRedTTS"><img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg" alt="Apache-2.0"></a>
+</div>
+
+## Overview
+
+FireRedTTS‑2 is a long-form streaming TTS system for **multi-speaker dialogue generation**, delivering stable, natural speech with reliable speaker switching and context-aware prosody.
+
+## Highlight🔥
+
+- **Long Conversational Speech Generation**: It currently supports 3 minutes dialogues with 4 speakers and can be easily scaled to longer conversations
+with more speakers by extending training corpus.
+- **Multilingual Support**: It supports multiple languages including English, Chinese, Japanese, Korean, French, German, and Russian. Support zero-shot voice cloning for cross-lingual and code-switching scenarios.
+- **Ultra-Low Latency**: Building on the new **12.5Hz streaming** speech tokenizer, we employ a dual-transformer architecture that operates on a text–speech interleaved sequence, enabling flexible sentence-bysentence generation and reducing first-packet latency，Specifically, on an L20 GPU, our first-packet latency as low as 140ms while maintaining high-quality audio output.
+- **Strong Stability**：Our model achieves high similarity and low WER/CER in both monologue and dialogue tests.
+- **Random Timbre Generation**:Useful for creating ASR/speech interaction data.
+
+## Demo Examples
+
+For more examples, see [demo page](https://fireredteam.github.io/demos/firered_tts_2/).
+
+## News
+
+- [2025/09/12] 🔥 **We have added a UI tool to the dialogue generation.**
+- [2025/09/08] 🔥 We release the [pre-trained checkpoints](https://huggingface.co/FireRedTeam/FireRedTTS2) and inference code.
+- [2025/09/02] 🔥 We release the [technical report](https://arxiv.org/abs/2509.02020) and [demo page](https://fireredteam.github.io/demos/firered_tts_2/)
+
+## Roadmap
+
+- [x] 2025/09
+  - [x] Release the pre-trained checkpoints and inference code.
+  - [x] Add web UI tool.
+
+- [ ] 2025/10
+  - [ ] Release a base model with enhanced multilingual support.
+  - [ ] **Provide fine-tuning code & tutorial for specific dialogue/multilingual data.**
+  - [ ] **End-to-end text-to-blog pipeline.**
+
+## Install & Model Download
+
+### Clone and install
+
+- **Clone the repo**
+
+    ``` sh
+    git clone https://github.com/FireRedTeam/FireRedTTS2.git
+    cd FireRedTTS2
+    ```
+
+- **Create Conda env**:
+
+    ``` sh
+    conda create --name fireredtts2 python==3.11
+    conda activate fireredtts2
+
+    # Step 1. PyTorch Installation (if required)
+    pip install torch==2.7.1 torchvision==0.22.1 torchaudio==2.7.1 --index-url https://download.pytorch.org/whl/cu126
+
+    # Step 2. Install Dependencies
+    pip install -e .
+    pip install -r requirements.txt
+    ```
+
+- **Model download**
+
+    ```sh
+    git lfs install
+    git clone https://huggingface.co/FireRedTeam/FireRedTTS2 pretrained_models/FireRedTTS2
+    ```
+
+## Basic Usage
+
+**Dialogue Generation with Web UI**
+
+Generate dialogue through an easy-to-use web interface that supports both voice cloning and randomized voices.
+
+```sh
+python gradio_demo.py --pretrained-dir "./pretrained_models/FireRedTTS2"
+```
+
+
+**Dialogue Generation**
+
+```python
+import os
+import sys
+import torch
+import torchaudio
+from fireredtts2.fireredtts2 import FireRedTTS2
+
+device = "cuda"
+
+fireredtts2 = FireRedTTS2(
+    pretrained_dir="./pretrained_models/FireRedTTS2",
+    gen_type="dialogue",
+    device=device,
+)
+
+text_list = [
+    "[S1]那可能说对对，没有去过美国来说去去看到美国线下。巴斯曼也好，沃尔玛也好，他们线下不管说，因为深圳出去的还是电子周边的会表达，会发现哇对这个价格真的是很高呀。都是卖三十五美金、四十美金，甚至一个手机壳，就是二十五美金开。",
+    "[S2]对，没错，我每次都觉得不不可思议。我什么人会买三五十美金的手机壳？但是其实在在那个target啊，就塔吉特这种超级市场，大家都是这样的，定价也很多人买。",
+    "[S1]对对，那这样我们再去看说亚马逊上面卖卖卖手机壳也好啊，贴膜也好，还包括说车窗也好，各种线材也好，大概就是七块九九或者说啊八块九九，这个价格才是卖的最多的啊。因为亚马逊的游戏规则限定的。如果说你卖七块九九以���，那你基本上是不赚钱的。",
+    "[S2]那比如说呃除了这个可能去到海外这个调查，然后这个调研考察那肯定是最直接的了。那平时我知道你是刚才建立了一个这个叫做呃rean的这样的一个一个播客，它是一个英文的。然后平时你还听一些什么样的东西，或者是从哪里获取一些这个海外市场的一些信息呢？",
+    "[S1]嗯，因为做做亚马逊的话呢，我们会关注很多行业内的东西。就比如说行业有什么样亚马逊有什么样新的游戏规则呀。呃，物流的价格有没有波动呀，包括说有没有什么新的评论的政策呀，广告有什么新的打法呀？那这些我们会会关关注很多行业内部的微信公众号呀，还包括去去查一些知乎专栏的文章呀，以及说我们周边有很多同行。那我们经常会坐在一起聊天，看看信息有什么共享。那这个是关注内内的一个方式。",
+]
+prompt_wav_list = [
+    "examples/chat_prompt/zh/S1.flac",
+    "examples/chat_prompt/zh/S2.flac",
+]
+
+prompt_text_list = [
+    "[S1]啊，可能说更适合美国市场应该是什么样子。那这这个可能说当然如果说有有机会能亲身的去考察去了解一下，那当然是有更好的帮助。",
+    "[S2]比如具体一点的，他觉得最大的一个跟他预想的不一样的是在什么地方。",
+]
+
+all_audio = fireredtts2.generate_dialogue(
+    text_list=text_list,
+    prompt_wav_list=prompt_wav_list,
+    prompt_text_list=prompt_text_list,
+    temperature=0.9,
+    topk=30,
+)
+torchaudio.save("chat_clone.wav", all_audio, 24000)
+```
+
+**Monologue Generation**
+
+```python
+import os
+import sys
+import torch
+import torchaudio
+from fireredtts2.fireredtts2 import FireRedTTS2
+
+device = "cuda"
+lines = [
+    "Hello everyone, welcome to our newly launched FireRedTTS2. It supports multiple languages including English, Chinese, Japanese, Korean, French, German, and Russian. Additionally, this TTS model features long-context dialogue generation capabilities.",
+    "如果你厌倦了千篇一律的AI音色，不满意于其他模型语言支持不够丰富，那么本项目将会成为你绝佳的工具。",
+    "ランダムな話者と言語を選択して合成できます",
+    "이는 많은 인공지능 시스템에 유용합니다. 예를 들어, 제가 다양한 음성 데이터를 대량으로 생성해 여러분의 ASR 모델이나 대화 모델에 풍부한 데이터를 제공할 수 있습니다.",
+    "J'évolue constamment et j'espère pouvoir parler davantage de langues avec plus d'aisance à l'avenir.",
+]
+
+fireredtts2 = FireRedTTS2(
+    pretrained_dir="./pretrained_models/FireRedTTS2",
+    gen_type="monologue",
+    device=device,
+)
+
+# random speaker
+for i in range(len(lines)):
+    text = lines[i].strip()
+    audio = fireredtts2.generate_monologue(text=text)
+    # adjust temperature & topk
+    # audio = fireredtts2.generate_monologue(text=text, temperature=0.8, topk=30)
+    torchaudio.save(str(i) + ".wav", audio.cpu(), 24000)
+
+
+# # voice clone
+# for i in range(len(lines)):
+#     text = lines[i].strip()
+
+#     audio = fireredtts2.generate_monologue(
+#         text=text,
+#         prompt_wav=<prompt_wav_path>,
+#         prompt_text=<prompt_wav_text>,
+#     )
+#     torchaudio.save(str(i) + ".wav", audio.cpu(), 24000)
+```
+
+## ⚠️ Usage Disclaimer ❗️❗️❗️❗️❗️❗️
+
+- The project incorporates zero-shot voice cloning functionality; Please note that this capability is intended **solely for academic research purposes**.
+- **DO NOT** use this model for **ANY illegal activities**❗️❗️❗️❗️❗️❗️
+- The developers assume no liability for any misuse of this model.
+- If you identify any instances of **abuse**, **misuse**, or **fraudulent** activities related to this project, **please report them to our team immediately.**

codec.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e0a31e0390d69e026f48e908eb5e74393c71e10f773998fcdac61abd60f5e21
+size 4298863130

config_codec.json

@@ -0,0 +1,63 @@
+{
+    "codec": {
+        "ssl_adaptor": {
+            "in_dim": 1280,
+            "embed_dim": 768,
+            "out_dim": 768,
+            "num_layers": 4,
+            "num_heads": 12,
+            "ffn_dim": 3072,
+            "attn_dropout": 0,
+            "dropout": 0
+        },
+        "acoustic_encoder": {
+            "num_mels": 128,
+            "sampling_rate": 16000,
+            "hop_length": 160,
+            "n_fft": 400,
+            "fmin": 0,
+            "fmax": 8000,
+            "embed_dim": 768,
+            "num_layers": 12,
+            "num_heads": 12,
+            "ffn_dim": 3072,
+            "attn_dropout": 0,
+            "dropout": 0,
+            "max_positions": 1500
+        },
+        "downsample": {
+            "embed_dim": 1536,
+            "avg_pooler": 4
+        },
+        "rvq": {
+            "input_dim": 1536,
+            "rvq_dim": 768,
+            "output_dim": 768,
+            "num_quantizers": 16,
+            "codebook_size": 2048,
+            "codebook_dim": 512
+        },
+        "upsample": {
+            "embed_dim": 768,
+            "stride": 4
+        },
+        "semantic_decoder": {
+            "in_dim": 768,
+            "embed_dim": 768,
+            "out_dim": 1280,
+            "num_layers": 4,
+            "num_heads": 12,
+            "ffn_dim": 3072,
+            "attn_dropout": 0,
+            "dropout": 0
+        },
+        "acoustic_decoder": {
+            "embed_dim": 768,
+            "num_layers": 12,
+            "num_heads": 12,
+            "dropout": 0,
+            "hop_length": 240,
+            "causal": true
+        }
+    }
+}

config_llm.json

@@ -0,0 +1,11 @@
+{
+    "llm_models": {
+        "sample_rate": 16000,
+        "backbone_flavor": "qwen-1.5b",
+        "decoder_flavor": "qwen-200m",
+        "text_vocab_size": 151936,
+        "audio_vocab_size": 2051,
+        "audio_num_codebooks": 16,
+        "decoder_loss_weight": 0.6
+    }
+}

llm_posttrain.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70f70632c028bb0396d479a340115d01e5f7a952451f283319a549d285ea0a7f
+size 8269965409

llm_pretrain.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:249681daf85dabb1d580913b27a9a4a82aa6f79d2cdfda0f955578aa70a8efd4
+size 8269965345