Upload 22 files

.gitattributes

@@ -37,3 +37,4 @@ models/diffusion_models/qwen-image-edit-2511-Q5_K_M.gguf filter=lfs diff=lfs mer
 models/diffusion_models/qwen-image-2512-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 models/LLM/Qwen3-VL-8B-Instruct-abliterated-v2.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text
 models/LLM/Qwen3-VL-8B-Instruct-abliterated-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/asset/dingding.png filter=lfs diff=lfs merge=lfs -text

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/blobs/dfc11073787daf1b0f9c0f1499487ab5f4c93738

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 20,
+  "transformers_version": "4.37.0"
+}

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/refs/main

@@ -0,0 +1 @@
+29e01c4e8d000f4bcd70751be16fa94bf3d85a18

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/.gitattributes

@@ -0,0 +1,36 @@
+*.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
+asset/dingding.png filter=lfs diff=lfs merge=lfs -text

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/CosyVoice-BlankEN/config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/CosyVoice-BlankEN/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 20,
+  "transformers_version": "4.37.0"
+}

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/CosyVoice-BlankEN/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130282af0dfa9fe5840737cc49a0d339d06075f83c5a315c3372c9a0740d0b96
+size 988097824

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/CosyVoice-BlankEN/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/README.md

@@ -0,0 +1,235 @@
+---
+license: apache-2.0
+language:
+- zh
+- en
+- fr
+- es
+- ja
+- ko
+- it
+- ru
+- de
+pipeline_tag: text-to-speech
+---
+
+![SVG Banners](https://svg-banners.vercel.app/api?type=origin&text1=CosyVoice🤠&text2=Text-to-Speech%20💖%20Large%20Language%20Model&width=800&height=210)
+
+## 👉🏻 CosyVoice 👈🏻
+
+**Fun-CosyVoice 3.0**: [Demos](https://funaudiollm.github.io/cosyvoice3/); [Paper](https://arxiv.org/abs/2505.17589); [Modelscope](https://www.modelscope.cn/models/FunAudioLLM/Fun-CosyVoice3-0.5B-2512); [Huggingface](https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512); [CV3-Eval](https://github.com/FunAudioLLM/CV3-Eval)
+
+**CosyVoice 2.0**: [Demos](https://funaudiollm.github.io/cosyvoice2/); [Paper](https://arxiv.org/abs/2412.10117); [Modelscope](https://www.modelscope.cn/models/iic/CosyVoice2-0.5B); [HuggingFace](https://huggingface.co/FunAudioLLM/CosyVoice2-0.5B)
+
+**CosyVoice 1.0**: [Demos](https://fun-audio-llm.github.io); [Paper](https://funaudiollm.github.io/pdf/CosyVoice_v1.pdf); [Modelscope](https://www.modelscope.cn/models/iic/CosyVoice-300M); [HuggingFace](https://huggingface.co/FunAudioLLM/CosyVoice-300M)
+
+## Highlight🔥
+
+**Fun-CosyVoice 3.0** is an advanced text-to-speech (TTS) system based on large language models (LLM), surpassing its predecessor (CosyVoice 2.0) in content consistency, speaker similarity, and prosody naturalness. It is designed for zero-shot multilingual speech synthesis in the wild.
+### Key Features
+- **Language Coverage**: Covers 9 common languages (Chinese, English, Japanese, Korean, German, Spanish, French, Italian, Russian), 18+ Chinese dialects/accents (Guangdong, Minnan, Sichuan, Dongbei, Shan3xi, Shan1xi, Shanghai, Tianjin, Shandong, Ningxia, Gansu, etc.) and meanwhile supports both multi-lingual/cross-lingual zero-shot voice cloning.
+- **Content Consistency & Naturalness**: Achieves state-of-the-art performance in content consistency, speaker similarity, and prosody naturalness.
+- **Pronunciation Inpainting**: Supports pronunciation inpainting of Chinese Pinyin and English CMU phonemes, providing more controllability and thus suitable for production use.
+- **Text Normalization**: Supports reading of numbers, special symbols and various text formats without a traditional frontend module.
+- **Bi-Streaming**: Support both text-in streaming and audio-out streaming, and achieves latency as low as 150ms while maintaining high-quality audio output.
+- **Instruct Support**: Supports various instructions such as languages, dialects, emotions, speed, volume, etc.
+
+
+## Roadmap
+
+- [x] 2025/12
+
+    - [x] release Fun-CosyVoice3-0.5B-2512 base model, rl model and its training/inference script
+    - [x] release Fun-CosyVoice3-0.5B modelscope gradio space
+
+- [x] 2025/08
+
+    - [x] Thanks to the contribution from NVIDIA Yuekai Zhang, add triton trtllm runtime support and cosyvoice2 grpo training support
+
+- [x] 2025/07
+
+    - [x] release Fun-CosyVoice 3.0 eval set
+
+- [x] 2025/05
+
+    - [x] add CosyVoice2-0.5B vllm support
+
+- [x] 2024/12
+
+    - [x] 25hz CosyVoice2-0.5B released
+
+- [x] 2024/09
+
+    - [x] 25hz CosyVoice-300M base model
+    - [x] 25hz CosyVoice-300M voice conversion function
+
+- [x] 2024/08
+
+    - [x] Repetition Aware Sampling(RAS) inference for llm stability
+    - [x] Streaming inference mode support, including kv cache and sdpa for rtf optimization
+
+- [x] 2024/07
+
+    - [x] Flow matching training support
+    - [x] WeTextProcessing support when ttsfrd is not available
+    - [x] Fastapi server and client
+
+## Evaluation
+
+| Model | Open-Source | Model Size | test-zh<br>CER (%) ↓ | test-zh<br>Speaker Similarity (%) ↑ | test-en<br>WER (%) ↓ | test-en<br>Speaker Similarity (%) ↑ | test-hard<br>CER (%) ↓ | test-hard<br>Speaker Similarity (%) ↑ |
+| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| Human | - | - | 1.26 | 75.5 | 2.14 | 73.4 | - | - |
+| Seed-TTS | ❌ | - | 1.12 | 79.6 | 2.25 | 76.2 | 7.59 | 77.6 |
+| MiniMax-Speech | ❌ | - | 0.83 | 78.3 | 1.65 | 69.2 | - | - |
+| F5-TTS | ✅ | 0.3B | 1.52 | 74.1 | 2.00 | 64.7 | 8.67 | 71.3 |
+| Spark TTS | ✅ | 0.5B | 1.2 | 66.0 | 1.98 | 57.3 | - | - |
+| CosyVoice2 | ✅ | 0.5B | 1.45 | 75.7 | 2.57 | 65.9 | 6.83 | 72.4 |
+| FireRedTTS2 | ✅ | 1.5B | 1.14 | 73.2 | 1.95 | 66.5 | - | - |
+| Index-TTS2 | ✅ | 1.5B | 1.03 | 76.5 | 2.23 | 70.6 | 7.12 | 75.5 |
+| VibeVoice-1.5B | ✅ | 1.5B | 1.16 | 74.4 | 3.04 | 68.9 | - | - |
+| VibeVoice-Realtime | ✅ | 0.5B | - | - | 2.05 | 63.3 | - | - |
+| HiggsAudio-v2 | ✅ | 3B | 1.50 | 74.0 | 2.44 | 67.7 | - | - |
+| VoxCPM | ✅ | 0.5B | 0.93 | 77.2 | 1.85 | 72.9 | 8.87 | 73.0 |
+| GLM-TTS | ✅ | 1.5B | 1.03 | 76.1 | - | - | - | - |
+| GLM-TTS RL | ✅ | 1.5B | 0.89 | 76.4 | - | - | - | - |
+| Fun-CosyVoice3-0.5B-2512 | ✅ | 0.5B | 1.21 | 78.0 | 2.24 | 71.8 | 6.71 | 75.8 |
+| Fun-CosyVoice3-0.5B-2512_RL | ✅ | 0.5B | 0.81 | 77.4 | 1.68 | 69.5 | 5.44 | 75.0 |
+
+
+## Install
+
+### Clone and install
+
+- Clone the repo
+    ``` sh
+    git clone --recursive https://github.com/FunAudioLLM/CosyVoice.git
+    # If you failed to clone the submodule due to network failures, please run the following command until success
+    cd CosyVoice
+    git submodule update --init --recursive
+    ```
+
+- Install Conda: please see https://docs.conda.io/en/latest/miniconda.html
+- Create Conda env:
+
+    ``` sh
+    conda create -n cosyvoice -y python=3.10
+    conda activate cosyvoice
+    pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
+
+    # If you encounter sox compatibility issues
+    # ubuntu
+    sudo apt-get install sox libsox-dev
+    # centos
+    sudo yum install sox sox-devel
+    ```
+
+### Model download
+
+``` python
+from huggingface_hub import snapshot_download
+snapshot_download('FunAudioLLM/Fun-CosyVoice3-0.5B-2512', local_dir='pretrained_models/Fun-CosyVoice3-0.5B')
+snapshot_download('FunAudioLLM/CosyVoice-ttsfrd', local_dir='pretrained_models/CosyVoice-ttsfrd')
+```
+
+Optionally, you can unzip `ttsfrd` resource and install `ttsfrd` package for better text normalization performance.
+
+Notice that this step is not necessary. If you do not install `ttsfrd` package, we will use wetext by default.
+
+``` sh
+cd pretrained_models/CosyVoice-ttsfrd/
+unzip resource.zip -d .
+pip install ttsfrd_dependency-0.1-py3-none-any.whl
+pip install ttsfrd-0.4.2-cp310-cp310-linux_x86_64.whl
+```
+
+### Basic Usage
+
+``` python
+import sys
+sys.path.append('third_party/Matcha-TTS')
+from cosyvoice.cli.cosyvoice import AutoModel
+import torchaudio
+
+""" CosyVoice3 Usage, check https://funaudiollm.github.io/cosyvoice3/ for more details
+"""
+cosyvoice = AutoModel(model_dir='pretrained_models/Fun-CosyVoice3-0.5B')
+# en zero_shot usage
+for i, j in enumerate(cosyvoice.inference_zero_shot('CosyVoice is undergoing a comprehensive upgrade, providing more accurate, stable, faster, and better voice generation capabilities.', 'You are a helpful assistant.<|endofprompt|>希望你以后能够做的比我还好呦。',
+                                                    './asset/zero_shot_prompt.wav', stream=False)):
+    torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+# zh zero_shot usage
+for i, j in enumerate(cosyvoice.inference_zero_shot('八百标兵奔北坡，北坡炮兵并排跑，炮兵怕把标兵碰，标兵怕碰炮兵炮。', 'You are a helpful assistant.<|endofprompt|>希望你以后能够做的比我还好呦。',
+                                                    './asset/zero_shot_prompt.wav', stream=False)):
+    torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+
+# fine grained control, for supported control, check cosyvoice/tokenizer/tokenizer.py#L280
+for i, j in enumerate(cosyvoice.inference_cross_lingual('You are a helpful assistant.<|endofprompt|>[breath]因为他们那一辈人[breath]在乡里面住的要习惯一点，[breath]邻居都很活络，[breath]嗯，都很熟悉。[breath]',
+                                                        './asset/zero_shot_prompt.wav', stream=False)):
+    torchaudio.save('fine_grained_control_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+
+# instruct usage, for supported control, check cosyvoice/utils/common.py#L28
+for i, j in enumerate(cosyvoice.inference_instruct2('好少咯，一般系放嗰啲国庆啊，中秋嗰啲可能会咯。', 'You are a helpful assistant. 请用广东话表达。<|endofprompt|>',
+                                                    './asset/zero_shot_prompt.wav', stream=False)):
+    torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+for i, j in enumerate(cosyvoice.inference_instruct2('收到好友从远方寄来的生日礼物，那份意外的惊喜与深深的祝福让我心中充满了甜蜜的快乐，笑容如花儿般绽放。', 'You are a helpful assistant. 请用尽可能快地语速说一句话。<|endofprompt|>',
+                                                    './asset/zero_shot_prompt.wav', stream=False)):
+    torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+
+# hotfix usage
+for i, j in enumerate(cosyvoice.inference_zero_shot('高管也通过电话、短信、微信等方式对报道[j][ǐ]予好评。', 'You are a helpful assistant.<|endofprompt|>希望你以后能够做的比我还好呦。',
+                                                    './asset/zero_shot_prompt.wav', stream=False)):
+    torchaudio.save('hotfix_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
+```
+
+## Discussion & Communication
+
+You can directly discuss on [Github Issues](https://github.com/FunAudioLLM/CosyVoice/issues).
+
+You can also scan the QR code to join our official Dingding chat group.
+
+<img src="./asset/dingding.png" width="250px">
+
+## Acknowledge
+
+1. We borrowed a lot of code from [FunASR](https://github.com/modelscope/FunASR).
+2. We borrowed a lot of code from [FunCodec](https://github.com/modelscope/FunCodec).
+3. We borrowed a lot of code from [Matcha-TTS](https://github.com/shivammehta25/Matcha-TTS).
+4. We borrowed a lot of code from [AcademiCodec](https://github.com/yangdongchao/AcademiCodec).
+5. We borrowed a lot of code from [WeNet](https://github.com/wenet-e2e/wenet).
+
+## Citations
+
+``` bibtex
+@article{du2024cosyvoice,
+  title={Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens},
+  author={Du, Zhihao and Chen, Qian and Zhang, Shiliang and Hu, Kai and Lu, Heng and Yang, Yexin and Hu, Hangrui and Zheng, Siqi and Gu, Yue and Ma, Ziyang and others},
+  journal={arXiv preprint arXiv:2407.05407},
+  year={2024}
+}
+
+@article{du2024cosyvoice,
+  title={Cosyvoice 2: Scalable streaming speech synthesis with large language models},
+  author={Du, Zhihao and Wang, Yuxuan and Chen, Qian and Shi, Xian and Lv, Xiang and Zhao, Tianyu and Gao, Zhifu and Yang, Yexin and Gao, Changfeng and Wang, Hui and others},
+  journal={arXiv preprint arXiv:2412.10117},
+  year={2024}
+}
+
+@article{du2025cosyvoice,
+  title={CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training},
+  author={Du, Zhihao and Gao, Changfeng and Wang, Yuxuan and Yu, Fan and Zhao, Tianyu and Wang, Hao and Lv, Xiang and Wang, Hui and Shi, Xian and An, Keyu and others},
+  journal={arXiv preprint arXiv:2505.17589},
+  year={2025}
+}
+
+@inproceedings{lyu2025build,
+  title={Build LLM-Based Zero-Shot Streaming TTS System with Cosyvoice},
+  author={Lyu, Xiang and Wang, Yuxuan and Zhao, Tianyu and Wang, Hao and Liu, Huadai and Du, Zhihao},
+  booktitle={ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  pages={1--2},
+  year={2025},
+  organization={IEEE}
+}
+```
+
+## Disclaimer
+The content provided above is for academic purposes only and is intended to demonstrate technical capabilities. Some examples are sourced from the internet. If any content infringes on your rights, please contact us to request its removal.

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/campplus.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ac6a63997761ae2997373e2ee1c47040854b4b759ea41ec48e4e42df0f4d73
+size 28303423

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/config.json

@@ -0,0 +1 @@
+{}

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-to-speech"}

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/cosyvoice3.yaml

@@ -0,0 +1,223 @@
+# set random seed, so that you may reproduce your result.
+__set_seed1: !apply:random.seed [1986]
+__set_seed2: !apply:numpy.random.seed [1986]
+__set_seed3: !apply:torch.manual_seed [1986]
+__set_seed4: !apply:torch.cuda.manual_seed_all [1986]
+
+# fixed params
+sample_rate: 24000
+llm_input_size: 896
+llm_output_size: 896
+spk_embed_dim: 192
+qwen_pretrain_path: ''
+token_frame_rate: 25
+token_mel_ratio: 2
+
+# stream related params
+chunk_size: 25 # streaming inference chunk size, in token
+num_decoding_left_chunks: -1 # streaming inference flow decoder left chunk size, <0 means use all left chunks
+
+# model params
+# for all class/function included in this repo, we use !<name> or !<new> for intialization, so that user may find all corresponding class/function according to one single yaml.
+# for system/third_party class/function, we do not require this.
+llm: !new:cosyvoice.llm.llm.CosyVoice3LM
+    llm_input_size: !ref <llm_input_size>
+    llm_output_size: !ref <llm_output_size>
+    speech_token_size: 6561
+    length_normalized_loss: True
+    lsm_weight: 0
+    mix_ratio: [5, 15]
+    llm: !new:cosyvoice.llm.llm.Qwen2Encoder
+        pretrain_path: !ref <qwen_pretrain_path>
+    sampling: !name:cosyvoice.utils.common.ras_sampling
+        top_p: 0.8
+        top_k: 25
+        win_size: 10
+        tau_r: 0.1
+
+flow: !new:cosyvoice.flow.flow.CausalMaskedDiffWithDiT
+    input_size: 80
+    output_size: 80
+    spk_embed_dim: !ref <spk_embed_dim>
+    output_type: 'mel'
+    vocab_size: 6561
+    input_frame_rate: !ref <token_frame_rate>
+    only_mask_loss: True
+    token_mel_ratio: !ref <token_mel_ratio>
+    pre_lookahead_len: 3
+    pre_lookahead_layer: !new:cosyvoice.transformer.upsample_encoder.PreLookaheadLayer
+        in_channels: 80
+        channels: 1024
+        pre_lookahead_len: 3
+    decoder: !new:cosyvoice.flow.flow_matching.CausalConditionalCFM
+        in_channels: 240
+        n_spks: 1
+        spk_emb_dim: 80
+        cfm_params: !new:omegaconf.DictConfig
+            content:
+                sigma_min: 1e-06
+                solver: 'euler'
+                t_scheduler: 'cosine'
+                training_cfg_rate: 0.2
+                inference_cfg_rate: 0.7
+                reg_loss_type: 'l1'
+        estimator: !new:cosyvoice.flow.DiT.dit.DiT
+            dim: 1024
+            depth: 22
+            heads: 16
+            dim_head: 64
+            ff_mult: 2
+            mel_dim: 80
+            mu_dim: 80
+            spk_dim: 80
+            out_channels: 80
+            static_chunk_size: !ref <chunk_size> * <token_mel_ratio>
+            num_decoding_left_chunks: !ref <num_decoding_left_chunks>
+
+hift: !new:cosyvoice.hifigan.generator.CausalHiFTGenerator
+    in_channels: 80
+    base_channels: 512
+    nb_harmonics: 8
+    sampling_rate: !ref <sample_rate>
+    nsf_alpha: 0.1
+    nsf_sigma: 0.003
+    nsf_voiced_threshold: 10
+    upsample_rates: [8, 5, 3]
+    upsample_kernel_sizes: [16, 11, 7]
+    istft_params:
+        n_fft: 16
+        hop_len: 4
+    resblock_kernel_sizes: [3, 7, 11]
+    resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+    source_resblock_kernel_sizes: [7, 7, 11]
+    source_resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+    lrelu_slope: 0.1
+    audio_limit: 0.99
+    conv_pre_look_right: 4
+    f0_predictor: !new:cosyvoice.hifigan.f0_predictor.CausalConvRNNF0Predictor
+        num_class: 1
+        in_channels: 80
+        cond_channels: 512
+
+# gan related module
+mel_spec_transform1: !name:matcha.utils.audio.mel_spectrogram
+    n_fft: 1920
+    num_mels: 80
+    sampling_rate: !ref <sample_rate>
+    hop_size: 480
+    win_size: 1920
+    fmin: 0
+    fmax: null
+    center: False
+hifigan: !new:cosyvoice.hifigan.hifigan.HiFiGan
+    generator: !ref <hift>
+    discriminator: !new:cosyvoice.hifigan.discriminator.MultipleDiscriminator
+        mpd: !new:matcha.hifigan.models.MultiPeriodDiscriminator
+        mrd: !new:cosyvoice.hifigan.discriminator.MultiResSpecDiscriminator
+    mel_spec_transform: [
+        !ref <mel_spec_transform1>
+    ]
+
+# processor functions
+parquet_opener: !name:cosyvoice.dataset.processor.parquet_opener
+get_tokenizer: !name:cosyvoice.tokenizer.tokenizer.get_qwen_tokenizer
+    token_path: !ref <qwen_pretrain_path>
+    skip_special_tokens: True
+    version: cosyvoice3
+allowed_special: 'all'
+tokenize: !name:cosyvoice.dataset.processor.tokenize
+    get_tokenizer: !ref <get_tokenizer>
+    allowed_special: !ref <allowed_special>
+filter: !name:cosyvoice.dataset.processor.filter
+    max_length: 40960
+    min_length: 100
+    token_max_length: 200
+    token_min_length: 1
+resample: !name:cosyvoice.dataset.processor.resample
+    resample_rate: !ref <sample_rate>
+truncate: !name:cosyvoice.dataset.processor.truncate
+    truncate_length: 24480 # must be a multiplier of hop_size
+feat_extractor: !name:matcha.utils.audio.mel_spectrogram
+    n_fft: 1920
+    num_mels: 80
+    sampling_rate: !ref <sample_rate>
+    hop_size: 480
+    win_size: 1920
+    fmin: 0
+    fmax: null
+    center: False
+compute_fbank: !name:cosyvoice.dataset.processor.compute_fbank
+    feat_extractor: !ref <feat_extractor>
+compute_f0: !name:cosyvoice.dataset.processor.compute_f0
+    sample_rate: !ref <sample_rate>
+    hop_size: 480
+parse_embedding: !name:cosyvoice.dataset.processor.parse_embedding
+    normalize: True
+shuffle: !name:cosyvoice.dataset.processor.shuffle
+    shuffle_size: 1000
+sort: !name:cosyvoice.dataset.processor.sort
+    sort_size: 500  # sort_size should be less than shuffle_size
+batch: !name:cosyvoice.dataset.processor.batch
+    batch_type: 'dynamic'
+    max_frames_in_batch: 2000
+padding: !name:cosyvoice.dataset.processor.padding
+    use_spk_embedding: False # change to True during sft
+
+
+# dataset processor pipeline
+data_pipeline: [
+    !ref <parquet_opener>,
+    !ref <tokenize>,
+    !ref <filter>,
+    !ref <resample>,
+    !ref <compute_fbank>,
+    !ref <parse_embedding>,
+    !ref <shuffle>,
+    !ref <sort>,
+    !ref <batch>,
+    !ref <padding>,
+]
+data_pipeline_gan: [
+    !ref <parquet_opener>,
+    !ref <tokenize>,
+    !ref <filter>,
+    !ref <resample>,
+    !ref <truncate>,
+    !ref <compute_fbank>,
+    !ref <compute_f0>,
+    !ref <parse_embedding>,
+    !ref <shuffle>,
+    !ref <sort>,
+    !ref <batch>,
+    !ref <padding>,
+]
+
+# llm flow train conf
+train_conf:
+    optim: adam
+    optim_conf:
+        lr: 1e-5 # change to 1e-5 during sft
+    scheduler: constantlr # change to constantlr during sft
+    scheduler_conf:
+        warmup_steps: 2500
+    max_epoch: 200
+    grad_clip: 5
+    accum_grad: 2
+    log_interval: 100
+    save_per_step: -1
+
+# gan train conf
+train_conf_gan:
+    optim: adam
+    optim_conf:
+        lr: 0.0002 # use small lr for gan training
+    scheduler: constantlr
+    optim_d: adam
+    optim_conf_d:
+        lr: 0.0002 # use small lr for gan training
+    scheduler_d: constantlr
+    max_epoch: 200
+    grad_clip: 5
+    accum_grad: 1 # in gan training, accum_grad must be 1
+    log_interval: 100
+    save_per_step: -1

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/flow.decoder.estimator.fp32.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b51b9533a55937762b262bf2cf9c6220ce40760f76d6532cb16a6a6d84059a8
+size 1326216933

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/flow.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6fab32a7825e5b0bc855ddd948f8db9370b0a786fbc249caa4595e95b608e4b
+size 1329116148

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/hift.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b279d7641eb97ae55b3b540cfba4f953c26492a2df758328a89a4d007ab87a65
+size 83202622

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/llm.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f43bd545131c30e98947fb360ea8b4dc9916d8e83dded7757c7ea4f5a24970
+size 2024669519

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/llm.rl.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74d34b01a80c7154670ae75ac372d1b1712c78bceae9f467eb9f1f6f61ec764f
+size 2024682701

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/speech_tokenizer_v3.batch.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b156b8a7bbff436585e153f4637b9a368009005ac66efa108a6c8bfb34e5ee43
+size 969451579

models/cosyvoice/Fun-CosyVoice3-0.5B/models--FunAudioLLM--Fun-CosyVoice3-0.5B-2512/snapshots/29e01c4e8d000f4bcd70751be16fa94bf3d85a18/speech_tokenizer_v3.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23236a74175dbdda47afc66dbadd5bcb41303c467a57c261cb8539ad9db9208d
+size 969451503