pyVideoTrans

English

简体中文

English

简体中文

Appearance

Win10/11 Pre-packaged Version Download ​

The latest version is v3.80, and the patch package is v3.80. From this version onwards, the maintenance and update frequency is reduced to once every two months.

Donate to the Developer, Help the Project Maintain Continuously

v3.80 Full Package Download (2.5G) ​

If you have not installed an older version, please download the full version here. If you need CUDA acceleration, you need to have an NVIDIA graphics card and install CUDA 12.x and cuDNN 9.

Baidu Netdisk Download: https://pan.baidu.com/s/1UiXiX-fGvOoua-s7cMpW5w?pwd=3y6g

huggingface.co: https://huggingface.co/mortimerme/repocollect/resolve/main/win-videotrans-v3.80.7z?download=true

v3.80 Patch Package (360MB) ​

Cannot be used alone, only used to overwrite old packages. The difference from the full package is that it does not contain the torch module. Since torch is upgraded from 2.5 to 2.7, the patch package does not contain torch. Directly downloading and overwriting the patch package may prevent CUDA acceleration. It is recommended to download the full package to overwrite.

Baidu Netdisk Download: https://pan.baidu.com/s/1EfLHFse3I9ejfk3gNveshw?pwd=bqfg

huggingface.co: https://huggingface.co/mortimerme/repocollect/resolve/main/win-PatchUpdate-3.80.7z?download=true

Extraction Notes:

  • Extract the 7z compressed package. After extraction, find the sp.exe file and double-click it to start the software.
  • Do not extract the software to the desktop or folders that require administrator rights, such as Program Files on the C drive.
  • Avoid path errors: Do not include Chinese characters, spaces, or special symbols in the extraction path.
  • If 7zip software prompts an error during extraction, please try using 360 compression software for extraction (https://yasuo.360.cn)

Online Q&A

faster-whisper Model Download Tool, Manually Download Models ​

By default, the software will automatically download the required models. If the download fails frequently, or you want to download manually, you can download the dedicated model download tool here.

  1. Download the tool:

    • For users in China (recommended):

    • For users overseas or with a stable proxy:

      • Click to download down_huggingface.exe
      • (Explanation: This version downloads from the Hugging Face official website, which requires you to be able to stably access the international internet or have a system proxy configured.)

  2. How to use:

    • Place the downloaded .exe file in the folder where the main program is located (together with sp.exe).
    • Double-click to run the .exe file you downloaded. It will open a command-line window and automatically start downloading all the required models.
    • The download process may take some time, especially the large series models are very large, so please wait patiently until the window prompts that everything is complete.

Important notes:

  • large-v1, large-v2, large-v3 and other models are very large (several GB). If your network is unstable, the download may fail midway.
  • If the download fails, don't worry, double-click the same .exe file again. It supports breakpoint resume and will continue downloading from where it failed last time.

MacOS/Linux System Source Code Deployment ​

The complete source code repository address of this software: https://github.com/jianchang512/pyvideotrans

Historical Versions Download