pyVideoTrans

Appearance

Linux Source Code Deployment ​

  1. Install ffmpeg. On CentOS, run yum install ffmpeg; on Ubuntu, run apt-get install ffmpeg.

  2. It is recommended to use uv for installation. If you do not have uv yet, install it by running the command curl -LsSf https://astral.sh/uv/install.sh | sh.

  3. Download the source code by executing the following commands:

    git clone https://github.com/jianchang512/pyvideotrans
cd pyvideotrans

  4. Run the command uv sync to install the modules. Depending on your network conditions, this may take several minutes to over ten minutes. Users in mainland China can use a mirror to speed up the installation with the command: uv sync --index https://mirrors.aliyun.com/pypi/simple/.

By default, local channels for qwen-tts, qwen-asr, moss-tts, and chatterbox are not installed. If needed, run uv sync --all-extra.

  1. Run the command uv run sp.py to open the software interface.

To use CUDA acceleration, execute the following commands respectively:

Example

uv remove torch torchaudio

uv add --reinstall torch torchaudio --index-url https://download.pytorch.org/whl/cu126

uv add nvidia-cublas-cu12 nvidia-cudnn-cu12