Hugging Peers

ChatTTS

☆ Save
by gggitxdx117 text-to-speech
135 downloads 3 likes on ModelScope updated

Model card

文本转语音模型

引用Github：https://github.com/CCmahua/ChatTTS-Enhanced

离线一键整合包

支持WIN、MAC

百度网盘

链接: https://pan.baidu.com/s/1DqvN2hHZ2uAmdjKCwKNmCQ?pwd=f5d4 提取码: f5d4

夸克网盘

链接：https://pan.quark.cn/s/4ee64af2aedb

Linux部署

克隆仓库地址

git clone https://github.com/CCmahua/ChatTTS-Enhanced.git ./
cd ChatTTS-Enhanced

需安装conda

conda create -n Dlab python=3.10
conda activate Dlab
conda install pytorch==2.1.1 torchvision==0.16.1 torchaudio==2.1.1 pytorch-cuda=11.8 -c pytorch -c nvidia

安装环境依赖

pip install resemble-enhance
pip install -r requirements.txt
pip install WeTextProcessing

运行命令

python webui/webui.py

项目根目录下创建config.ini文件

[server]
custom_server = true
ip = 0.0.0.0
port = 8080

可修改项目根目录下的./processors/model_processor.py

  • 注释第8行代码并增加指定模型目录，目录按实际保存的即可
    # chat.load_models()
    chat.load_models(source=local, local_path='/home/ubuntu/ChatTTS-Enhanced/model/')

感谢

  • CCmahua：https://github.com/CCmahua/ChatTTS-Enhanced
  • ChatTTS:https://github.com/2noise/ChatTTS
  • Resemble Enhance:https://github.com/resemble-ai/resemble-enhance
  • ChatTTS_colab:https://github.com/6drf21e/ChatTTS_colab
  • PaddleSpeech:https://github.com/PaddlePaddle/PaddleSpeech
  • ChatTTS_Speaker:https://github.com/6drf21e/ChatTTS_Speaker
  • WeTextProcessing:https://github.com/wenet-e2e/WeTextProcessing