Cosyvoice2 0.5B

🚀 CosyVoice

CosyVoice 是一个文本转语音的工具库，支持多语言零样本、跨语言推理，提供流式推理模式，可用于语音合成、语音转换等多种场景。

🚀 快速开始

模型演示与文档

• CosyVoice2 演示
  • CosyVoice2 论文
  • CosyVoice2 工作室
• CosyVoice 演示
  • CosyVoice 论文
  • CosyVoice 工作室
  • CosyVoice 代码

关于 SenseVoice，请访问 SenseVoice 仓库 和 SenseVoice 空间。

路线图

• 2024/12
  • [x] CosyVoice2 - 0.5B 模型发布
  • [x] CosyVoice2 - 0.5B 流式推理且质量不下降
• 2024/07
  • [x] 支持流匹配训练
  • [x] 当 ttsfrd 不可用时支持 WeTextProcessing
  • [x] Fastapi 服务器和客户端
• 2024/08
  • [x] 支持重复感知采样（RAS）推理以提高大语言模型稳定性
  • [x] 支持流式推理模式，包括 kv 缓存和 sdpa 以优化实时因子
• 2024/09
  • [x] 25hz CosyVoice 基础模型
  • [x] 25hz CosyVoice 语音转换模型
• 待确定
  • [ ] 支持 CosyVoice2 - 0.5B 双流推理
  • [ ] CosyVoice2 - 0.5B 训练和微调方案
  • [ ] 使用更多多语言数据训练的 CosyVoice - 500M
  • [ ] 更多...

📦 安装指南

克隆并安装

git clone --recursive https://github.com/FunAudioLLM/CosyVoice.git
# 如果由于网络问题克隆子模块失败，请运行以下命令直到成功
cd CosyVoice
git submodule update --init --recursive

安装 Conda：请参考 Conda 安装文档。 创建 Conda 环境：

conda create -n cosyvoice python=3.10
conda activate cosyvoice
# WeTextProcessing 需要 pynini，使用 conda 安装以确保在所有平台上都能执行
conda install -y -c conda-forge pynini==2.1.5
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com

# 如果遇到 sox 兼容性问题
# ubuntu
sudo apt-get install sox libsox-dev
# centos
sudo yum install sox sox-devel

模型下载

强烈建议下载预训练的 CosyVoice - 300M、CosyVoice - 300M - SFT、CosyVoice - 300M - Instruct 模型和 CosyVoice - ttsfrd 资源。 如果您是该领域的专家，并且只对从头开始训练自己的 CosyVoice 模型感兴趣，可以跳过此步骤。

Python SDK 下载

# SDK模型下载
from modelscope import snapshot_download
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-25Hz', local_dir='pretrained_models/CosyVoice-300M-25Hz')
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')

Git 下载

# 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-25Hz.git pretrained_models/CosyVoice-300M-25Hz
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

可选步骤：可以解压 ttsfrd 资源并安装 ttsfrd 包以获得更好的文本规范化性能。 注意，此步骤不是必需的。如果不安装 ttsfrd 包，默认将使用 WeTextProcessing。

cd pretrained_models/CosyVoice-ttsfrd/
unzip resource.zip -d .
pip install ttsfrd-0.3.6-cp38-cp38-linux_x86_64.whl

💻 使用示例

基础用法

对于零样本/跨语言推理，请使用 CosyVoice2 - 0.5B 或 CosyVoice - 300M 模型；对于 SFT 推理，请使用 CosyVoice - 300M - SFT 模型；对于指令推理，请使用 CosyVoice - 300M - Instruct 模型。强烈建议使用 CosyVoice2 - 0.5B 模型以获得更好的流式性能。

首先，将 third_party/Matcha - TTS 添加到 PYTHONPATH：

export PYTHONPATH=third_party/Matcha-TTS

from cosyvoice.cli.cosyvoice import CosyVoice, CosyVoice2
from cosyvoice.utils.file_utils import load_wav
import torchaudio

## cosyvoice2 usage
cosyvoice2 = CosyVoice('pretrained_models/CosyVoice-300M-SFT', load_jit=False, load_onnx=False, load_trt=False)
# sft usage
prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
for i, j in enumerate(cosyvoice2.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=True)):
    torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice2.sample_rate)

## cosyvoice usage
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT', load_jit=True, load_onnx=False, fp16=True)
# sft usage
print(cosyvoice.list_avaliable_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-25Hz') # or change to pretrained_models/CosyVoice-300M for 50Hz inference
# zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
prompt_speech_16k = load_wav('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('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('zero_shot_prompt.wav', 16000)
source_speech_16k = load_wav('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)

启动 Web 演示

可以使用 Web 演示页面快速熟悉 CosyVoice。Web 演示支持 SFT/零样本/跨语言/指令推理。

# change iic/CosyVoice-300M-SFT for sft inference, or iic/CosyVoice-300M-Instruct for instruct inference
python3 webui.py --port 50000 --model_dir pretrained_models/CosyVoice-300M

高级用法

对于高级用户，在 examples/libritts/cosyvoice/run.sh 中提供了训练和推理脚本，可以按照该脚本熟悉 CosyVoice。

构建部署

如果想使用 gRPC 进行服务部署，可以执行以下步骤，否则可以忽略此步骤。

cd runtime/python
docker build -t cosyvoice:v1.0 .
# change iic/CosyVoice-300M to iic/CosyVoice-300M-Instruct if you want to use instruct inference
# for grpc usage
docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c "cd /opt/CosyVoice/CosyVoice/runtime/python/grpc && python3 server.py --port 50000 --max_conc 4 --model_dir iic/CosyVoice-300M && sleep infinity"
cd grpc && python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>
# for fastapi usage
docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c "cd /opt/CosyVoice/CosyVoice/runtime/python/fastapi && python3 server.py --port 50000 --model_dir iic/CosyVoice-300M && sleep infinity"
cd fastapi && python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>

📚 详细文档

讨论与交流

可以直接在 Github Issues 上进行讨论，也可以扫描二维码加入官方钉钉聊天群。

致谢

本项目借鉴了以下项目的很多代码：

1. FunASR
2. FunCodec
3. Matcha - TTS
4. AcademiCodec
5. WeNet

引用

@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}
}

免责声明

以上内容仅用于学术目的，旨在展示技术能力。部分示例来源于互联网，如果任何内容侵犯了您的权益，请联系我们要求删除。