v3.83

jianchang512/pyvideotransv3.83Nov 1, 2025by jianchang512

AI Summary

Windows release providing a 3.8G full package including the large-v3-turbo model and a smaller patch, with specific hardware requirements for CUDA acceleration.

Key Highlights

Full package includes large-v3-turbo model
Patch package excludes torch module
Requires NVIDIA GPU + CUDA 12.8/cuDNN 9 for acceleration

New Features

Includes large-v3-turbo model

Full Release Notes

> The pre-packaged version is only for Windows 10/11. [For macOS and Linux, please deploy from source](https://pyvideotrans.com/mac)
> To upgrade a source deployment: pull the source code again to overwrite, then execute `pip3 install --upgrade torch openai google-genai whisper elevenlabs gradio_client faster-whisper`




## v3.84 Full Package Download (3.8G Includes large-v3-turbo model)

> If this is a fresh installation, please download the full package. For CUDA acceleration, an NVIDIA graphics card is required, along with CUDA 12.8 and cuDNN 9.


huggingface.co: https://huggingface.co/mortimerme/repocollect/resolve/main/win-videotrans-v3.83.7z?download=true

Baidu Network Disk: https://pan.baidu.com/s/1_Oz9DbpwYR9-eBmalCj7UQ?pwd=cwdm


## v3.84 Patch Package (360MB)

> Cannot be used standalone; this is only for overwriting a previous installation. The main difference from the full package is that it does not contain the `torch` module.
> Since `torch` has been upgraded from 2.5 to 2.7, this patch does not include it. Applying the patch directly may cause CUDA acceleration to fail. It is recommended to download the full package to update.

huggingface.co: https://huggingface.co/mortimerme/repocollect/resolve/main/win-PatchUpdate-3.83.7z?download=true

Baidu Network Disk: https://pan.baidu.com/s/1KEfJnoJp8Vavj_T3_jxs1w?pwd=anf7