deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-04 09:29:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into main

Browse Source
This commit is contained in:
Xiang Lyu
2025-12-31 10:37:18 +08:00
committed by GitHub
parent 6816fc6a6f dac6566fc3
commit f88a14e41d
44 changed files with 2476 additions and 591 deletions
Download Patch File Download Diff File Expand all files Collapse all files

173
README.md
View File

@@ -1,54 +1,52 @@
[![SVG Banners](https://svg-banners.vercel.app/api?type=origin&text1=CosyVoice🤠&text2=Text-to-Speech%20💖%20Large%20Language%20Model&width=800&height=210)](https://github.com/Akshay090/svg-banners)
![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 👈🏻
**CosyVoice 3.0**: [Demos](https://funaudiollm.github.io/cosyvoice3/); [Paper](https://arxiv.org/abs/2505.17589); [CV3-Eval](https://github.com/FunAudioLLM/CV3-Eval)
**Fun-CosyVoice 3.0**: [Demos](https://funaudiollm.github.io/cosyvoice3/); [Paper](https://arxiv.org/pdf/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/studios/iic/CosyVoice2-0.5B); [HuggingFace](https://huggingface.co/spaces/FunAudioLLM/CosyVoice2-0.5B)
**CosyVoice 2.0**: [Demos](https://funaudiollm.github.io/cosyvoice2/); [Paper](https://arxiv.org/pdf/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/studios/iic/CosyVoice-300M)
**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🔥
**CosyVoice 2.0** has been released! Compared to version 1.0, the new version offers more accurate, more stable, faster, and better speech generation capabilities.
### Multilingual
- **Supported Language**: Chinese, English, Japanese, Korean, Chinese dialects (Cantonese, Sichuanese, Shanghainese, Tianjinese, Wuhanese, etc.)
- **Crosslingual & Mixlingual**：Support zero-shot voice cloning for cross-lingual and code-switching scenarios.
### Ultra-Low Latency
- **Bidirectional Streaming Support**: CosyVoice 2.0 integrates offline and streaming modeling technologies.
- **Rapid First Packet Synthesis**: Achieves latency as low as 150ms while maintaining high-quality audio output.
### High Accuracy
- **Improved Pronunciation**: Reduces pronunciation errors by 30% to 50% compared to CosyVoice 1.0.
- **Benchmark Achievements**: Attains the lowest character error rate on the hard test set of the Seed-TTS evaluation set.
### Strong Stability
- **Consistency in Timbre**: Ensures reliable voice consistency for zero-shot and cross-language speech synthesis.
- **Cross-language Synthesis**: Marked improvements compared to version 1.0.
### Natural Experience
- **Enhanced Prosody and Sound Quality**: Improved alignment of synthesized audio, raising MOS evaluation scores from 5.4 to 5.53.
- **Emotional and Dialectal Flexibility**: Now supports more granular emotional controls and accent adjustments.
**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 cosyvoice 3.0 eval set
- [x] release Fun-CosyVoice 3.0 eval set
- [x] 2025/05
- [x] add cosyvoice 2.0 vllm support
- [x] add CosyVoice2-0.5B vllm support
- [x] 2024/12
- [x] 25hz cosyvoice 2.0 released
- [x] 25hz CosyVoice2-0.5B released
- [x] 2024/09
- [x] 25hz cosyvoice base model
- [x] 25hz cosyvoice voice conversion model
- [x] 25hz CosyVoice-300M base model
- [x] 25hz CosyVoice-300M voice conversion function
- [x] 2024/08
@@ -61,6 +59,27 @@
- [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
@@ -91,26 +110,26 @@
### Model download
We strongly recommend that you download our pretrained `CosyVoice2-0.5B` `CosyVoice-300M` `CosyVoice-300M-SFT` `CosyVoice-300M-Instruct` model and `CosyVoice-ttsfrd` resource.
We strongly recommend that you download our pretrained `Fun-CosyVoice3-0.5B` `CosyVoice2-0.5B` `CosyVoice-300M` `CosyVoice-300M-SFT` `CosyVoice-300M-Instruct` model and `CosyVoice-ttsfrd` resource.
``` python
# SDK模型下载
# modelscope SDK model download
from modelscope import snapshot_download
snapshot_download('FunAudioLLM/Fun-CosyVoice3-0.5B-2512', local_dir='pretrained_models/Fun-CosyVoice3-0.5B')
snapshot_download('iic/CosyVoice2-0.5B', local_dir='pretrained_models/CosyVoice2-0.5B')
snapshot_download('iic/CosyVoice-300M', local_dir='pretrained_models/CosyVoice-300M')
snapshot_download('iic/CosyVoice-300M-SFT', local_dir='pretrained_models/CosyVoice-300M-SFT')
snapshot_download('iic/CosyVoice-300M-Instruct', local_dir='pretrained_models/CosyVoice-300M-Instruct')
snapshot_download('iic/CosyVoice-ttsfrd', local_dir='pretrained_models/CosyVoice-ttsfrd')
```
``` sh
# git模型下载，请确保已安装git lfs
mkdir -p pretrained_models
git clone https://www.modelscope.cn/iic/CosyVoice2-0.5B.git pretrained_models/CosyVoice2-0.5B
git clone https://www.modelscope.cn/iic/CosyVoice-300M.git pretrained_models/CosyVoice-300M
git clone https://www.modelscope.cn/iic/CosyVoice-300M-SFT.git pretrained_models/CosyVoice-300M-SFT
git clone https://www.modelscope.cn/iic/CosyVoice-300M-Instruct.git pretrained_models/CosyVoice-300M-Instruct
git clone https://www.modelscope.cn/iic/CosyVoice-ttsfrd.git pretrained_models/CosyVoice-ttsfrd
# for oversea users, huggingface SDK model download
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/CosyVoice2-0.5B', local_dir='pretrained_models/CosyVoice2-0.5B')
snapshot_download('FunAudioLLM/CosyVoice-300M', local_dir='pretrained_models/CosyVoice-300M')
snapshot_download('FunAudioLLM/CosyVoice-300M-SFT', local_dir='pretrained_models/CosyVoice-300M-SFT')
snapshot_download('FunAudioLLM/CosyVoice-300M-Instruct', local_dir='pretrained_models/CosyVoice-300M-Instruct')
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.
@@ -126,50 +145,10 @@ pip install ttsfrd-0.4.2-cp310-cp310-linux_x86_64.whl
### Basic Usage
We strongly recommend using `CosyVoice2-0.5B` for better performance.
Follow the code below for detailed usage of each model.
``` python
import sys
sys.path.append('third_party/Matcha-TTS')
from cosyvoice.cli.cosyvoice import CosyVoice, CosyVoice2
from cosyvoice.utils.file_utils import load_wav
import torchaudio
```
#### CosyVoice2 Usage
```python
cosyvoice = CosyVoice2('pretrained_models/CosyVoice2-0.5B', load_jit=False, load_trt=False, load_vllm=False, fp16=False)
# NOTE if you want to reproduce the results on https://funaudiollm.github.io/cosyvoice2, please add text_frontend=False during inference
# zero_shot usage
prompt_speech_16k = load_wav('./asset/zero_shot_prompt.wav', 16000)
for i, j in enumerate(cosyvoice.inference_zero_shot('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。', '希望你以后能够做的比我还好呦。', prompt_speech_16k, stream=False)):
torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
# save zero_shot spk for future usage
assert cosyvoice.add_zero_shot_spk('希望你以后能够做的比我还好呦。', prompt_speech_16k, 'my_zero_shot_spk') is True
for i, j in enumerate(cosyvoice.inference_zero_shot('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。', '', '', zero_shot_spk_id='my_zero_shot_spk', stream=False)):
torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
cosyvoice.save_spkinfo()
# fine grained control, for supported control, check cosyvoice/tokenizer/tokenizer.py#L248
for i, j in enumerate(cosyvoice.inference_cross_lingual('在他讲述那个荒诞故事的过程中，他突然[laughter]停下来，因为他自己也被逗笑了[laughter]。', prompt_speech_16k, stream=False)):
torchaudio.save('fine_grained_control_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
# instruct usage
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。', '用四川话说这句话', prompt_speech_16k, stream=False)):
torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
# bistream usage, you can use generator as input, this is useful when using text llm model as input
# NOTE you should still have some basic sentence split logic because llm can not handle arbitrary sentence length
def text_generator():
yield '收到好友从远方寄来的生日礼物，'
yield '那份意外的惊喜与深深的祝福'
yield '让我心中充满了甜蜜的快乐，'
yield '笑容如花儿般绽放。'
for i, j in enumerate(cosyvoice.inference_zero_shot(text_generator(), '希望你以后能够做的比我还好呦。', prompt_speech_16k, stream=False)):
torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
We strongly recommend using `Fun-CosyVoice3-0.5B` for better performance.
Follow the code in `example.py` for detailed usage of each model.
```sh
python example.py
```
#### CosyVoice2 vllm Usage
@@ -182,42 +161,12 @@ Notice that `vllm==v0.9.0` has a lot of specific requirements, for example `torc
conda create -n cosyvoice_vllm --clone cosyvoice
conda activate cosyvoice_vllm
# for vllm==0.9.0
pip install vllm==v0.9.0 transformers==4.51.3 -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
pip install vllm==v0.9.0 transformers==4.51.3 numpy==1.26.4 -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
# for vllm>=0.11.0
pip install vllm==v0.11.0 transformers==4.57.1 -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
pip install vllm==v0.11.0 transformers==4.57.1 numpy==1.26.4 -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
python vllm_example.py
```
#### CosyVoice Usage
```python
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT', load_jit=False, load_trt=False, fp16=False)
# sft usage
print(cosyvoice.list_available_spks())
# change stream=True for chunk stream inference
for i, j in enumerate(cosyvoice.inference_sft('你好，我是通义生成式语音大模型，请问有什么可以帮您的吗？', '中文女', stream=False)):
torchaudio.save('sft_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M')
# zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
prompt_speech_16k = load_wav('./asset/zero_shot_prompt.wav', 16000)
for i, j in enumerate(cosyvoice.inference_zero_shot('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。', '希望你以后能够做的比我还好呦。', prompt_speech_16k, stream=False)):
torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
# cross_lingual usage
prompt_speech_16k = load_wav('./asset/cross_lingual_prompt.wav', 16000)
for i, j in enumerate(cosyvoice.inference_cross_lingual('<|en|>And then later on, fully acquiring that company. So keeping management in line, interest in line with the asset that\'s coming into the family is a reason why sometimes we don\'t buy the whole thing.', prompt_speech_16k, stream=False)):
torchaudio.save('cross_lingual_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
# vc usage
prompt_speech_16k = load_wav('./asset/zero_shot_prompt.wav', 16000)
source_speech_16k = load_wav('./asset/cross_lingual_prompt.wav', 16000)
for i, j in enumerate(cosyvoice.inference_vc(source_speech_16k, prompt_speech_16k, stream=False)):
torchaudio.save('vc_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-Instruct')
# instruct usage, support <laughter></laughter><strong></strong>[laughter][breath]
for i, j in enumerate(cosyvoice.inference_instruct('在面对挑战时，他展现了非凡的<strong>勇气</strong>与<strong>智慧</strong>。', '中文男', 'Theo \'Crimson\', is a fiery, passionate rebel leader. Fights with fervor for justice, but struggles with impulsiveness.', stream=False)):
torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
```
#### Start web demo
You can use our web demo page to get familiar with CosyVoice quickly.