yuhaolove / chattts-webui Goto Github PK

Batchfile 11.01% Python 88.99%

chattts-webui's Introduction

ChatTTS-WebUI

Project Introduction

This is an AI project that depends on the ChatTTS project. The project includes a web user interface that allows users to interact with the model through the interface.

If you find it useful, please give it a star.

Project Structure

my_ai_project/
│
├── ChatTTS               # Cloned directory of the ChatTTS project
│  └── ChatTTS            
│      ├── experimental   
│      ├── infer          
│      ├── model          
│      └── utils          
├── environment           # Virtual environment directory, contains all dependencies
├── models                # Model files directory
│  ├── asset              
│  └── config             
├── outputs               # Output files directory (e.g., logs, results, etc.)
├── webui                 # Web user interface code directory
│  ├── main.py            # Main entry file for the web user interface
│  └── ...                # Other files related to the web user interface
├── install.bat           # One-click installation script for installing and configuring the project
├── run_webui.bat         # Script to start the web user interface
├── update.bat            # Script to update the ChatTTS project
├── update_chatts.py      # Python script to update the ChatTTS project
└── requirements.txt      # Project dependencies file

Installation

Manual Installation

Install Conda: Download and install Miniconda or Anaconda from the Conda official website.

Clone this project:

git clone https://github.com/yuhaolove/ChatTTS-WebUI.git

Create and activate a virtual environment:

cd ChatTTS-WebUI
conda create -n chattts_webui python=3.12.3
conda activate chattts_webui

Clone the ChatTTS repository:

cd ChatTTS-WebUI
git clone https://github.com/2noise/ChatTTS.git

Install ChatTTS dependencies:

cd ChatTTS
pip install -r requirements.txt
cd ..

Install this project's WebUI dependencies:
```
pip install -r requirements.txt
```

One-click Installation Package on Windows

Download and run the installation script: Click here to download the one-click installation package. Download For first-time use, double-click or run install.bat in the command line. The installation will complete and directly start the webui. For subsequent use, just double-click run_webui.bat.

Start the WebUI

On Windows

Double-click or run run_webui.bat in the command line to start the Web user interface:

run_webui.bat

On Other Systems

Not tested yet, you can directly use Conda's Python to start it:

python webui/main.py

Manual Installation of Model Files

If you cannot download the HF model files smoothly, you can download them manually and place them in the corresponding directory.

Download model files: Go to the model download page to download the model files.

Place the files in the corresponding directory:

├─models
│  ├─asset
│  └─config

Notes

Make sure you have a stable network connection to download dependencies and clone repositories.

Contact

If you have any questions or need help, please contact [浩哥聊AI].

Support

If you find this project helpful, please consider giving some support. Your support will help me continue to develop and maintain this project, and bring more useful features and improvements.

You can also scan the following QR codes to support:

Alipay	WeChat Pay

Acknowledgments

The names of all supporters (if willing to be public) will be recorded in the project's acknowledgment list. Thank you for your support!

chattts-webui's People

Contributors

Stargazers

Watchers

chattts-webui's Issues

手动克隆模型放到指定目录没生效，还是会从远端下载

从 README 中的 https://www.modelscope.cn/models/pzc163/chatTTS/files 克隆模型放进去没生效
看代码会校验文件是否齐全，如果不齐全的话会从远端下载，排查发现 asset 目录缺 spk_stat.pt

从这里下载补进去就好了 https://huggingface.co/2Noise/ChatTTS/blob/main/asset/spk_stat.pt

希望能加上音色选择，或者怎么使用自己选的某个B站UP主的音色

如题，谢谢！

ModuleNotFoundError: No module named 'nemo_text_processing'

这个包安装失败，无法生成语音

install error

install.bat

python update_chattts.py 没有这个文件实际文件是update.py？

然后最好安装的时候让用户选择是否需要科学上网，不然下载不了东西安装失败。

项目运行后，有些疑问

会形成一个https://xxxxxx.gradio.live的临时链接，这个可以自己关闭吗？
这个项目怎么改成GPU运行，现在好像是CPU在运行？

python webui/main.py

Load models from snapshot.
INFO:ChatTTS.core:Load from cache: /Users/yidian/.cache/huggingface/hub/models--2Noise--ChatTTS/snapshots/c0aa9139945a4d7bb1c84f07785db576f2bb1bfa
Traceback (most recent call last):
File "/Users/yidian/ChatTTS-WebUI/webui/main.py", line 39, in
chat.load_models()
File "/Users/yidian/ChatTTS-WebUI/ChatTTS/ChatTTS/core.py", line 55, in load_models
self.load(**{k: os.path.join(download_path, v) for k, v in OmegaConf.load(os.path.join(download_path, 'config', 'path.yaml')).items()})
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/yidian/PycharmProjects/pythonProject3/.venv/lib/python3.12/site-packages/omegaconf/omegaconf.py", line 189, in load
with io.open(os.path.abspath(file), "r", encoding="utf-8") as f:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [Errno 2] No such file or directory: '/Users/yidian/.cache/huggingface/hub/models--2Noise--ChatTTS/snapshots/c0aa9139945a4d7bb1c84f07785db576f2bb1bfa/config/path.yaml'
(chattts_webui) (.venv) yidian@ai ChatTTS-WebUI %

cannot access local variable 'Normalizer' where it is not associated with a value

UI打开之后无法进行转语音，转了就报错

RuntimeError: Dynamo is not supported on Python 3.12+

Traceback (most recent call last):
File "C:\Users\caoc\AI\ChatTTS-WebUI\webui\main.py", line 39, in
chat.load_models()
File "C:\Users\caoc\AI\ChatTTS-WebUI\ChatTTS\ChatTTS\core.py", line 61, in load_models
self._load(**{k: os.path.join(download_path, v) for k, v in OmegaConf.load(os.path.join(download_path, 'config', 'path.yaml')).items()}, **kwargs)
File "C:\Users\caoc\AI\ChatTTS-WebUI\ChatTTS\ChatTTS\core.py", line 102, in load
gpt.gpt.forward = torch.compile(gpt.gpt.forward, backend='inductor', dynamic=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\caoc\miniconda3\envs\chattts_webui\Lib\site-packages\torch_init.py", line 1866, in compile
raise RuntimeError("Dynamo is not supported on Python 3.12+")
RuntimeError: Dynamo is not supported on Python 3.12+