CosyVoice：开源强大的 AI 语音合成工具

在当今科技飞速发展的时代，AI 语音合成技术正逐渐改变着我们的生活。今天，就为大家介绍一款卓越的语音合成工具——CosyVoice。

一、安装步骤

1. 克隆和安装：
   • 克隆仓库：git clone --recursive https://github.com/FunAudioLLM/CosyVoice.git。如果克隆子模块失败，可以运行命令cd CosyVoice; git submodule update --init --recursive。
2. 安装 Conda：请参考https://docs.conda.io/en/latest/miniconda.html。
3. 创建 Conda 环境：
   • conda create -n cosyvoice python=3.8。
   • conda activate cosyvoice。
   • 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。
4. 解决 sox 兼容性问题：
   • Ubuntu：sudo apt-get install sox libsox-dev。
   • CentOS：sudo yum install sox sox-devel。

二、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。

1. SDK 模型下载：

   from modelscope import snapshot_download
   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')
   

2. git 模型下载（确保已安装 git lfs）：

   mkdir -p pretrained_models
   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
   

3. 可选步骤：解压ttsfrd资源并安装ttsfrd包以获得更好的文本归一化性能，但这不是必需的。若不安装，将默认使用WeTextProcessing。

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

三、基本用法

1. 对于不同的推理需求选择不同的模型：
   • 零样本/跨语言推理，请使用CosyVoice - 300M模型。
   • SFT 推理，请使用CosyVoice - 300M - SFT模型。
   • 指令推理，请使用CosyVoice - 300M - Instruct模型。
2. 首先，将third_party/Matcha - TTS添加到PYTHONPATH。

   export PYTHONPATH=third_party/Matcha - TTS
   

3. 示例代码：

   from cosyvoice.cli.cosyvoice import CosyVoice
   from cosyvoice.utils.file_utils import load_wav
   import torchaudio
   
   cosyvoice = CosyVoice('pretrained_models/CosyVoice - 300M - SFT')
   # 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'], 22050)
   
   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('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'], 22050)
   # 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'], 22050)
   
   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'], 22050)
   

四、启动 Web 演示

可以使用 Web 演示页面快速熟悉 CosyVoice，支持 sft/零样本/跨语言/指令推理。具体详情请参考演示网站。
示例命令：python3 webui.py --port 50000 --model_dir pretrained_models/CosyVoice - 300M（可根据需要更改模型）。

五、高级用法

对于高级用户，examples/libritts/cosyvoice/run.sh中提供了训练和推理脚本，可以按照此示例熟悉 CosyVoice。

六、构建用于部署

若要使用 grpc 进行服务部署，可执行以下步骤，否则可忽略此步骤。

1. 构建 docker 镜像：

   cd runtime/python
   docker build -t cosyvoice:v1.0.
   

2. 运行 docker 容器（根据需要选择推理模式）：
   • grpc 用法：

     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>
     

   • fastapi 用法：

     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>
     

CosyVoice 以其强大的功能和灵活的使用方式，为我们带来了全新的语音合成体验。快来尝试吧！