Starstruk Logo MarkStarstruk

v3.47

jianchang512/pyvideotransv3.47Feb 3, 2025by jianchang512

AI Summary

Added GLM-4 Flash and Qwen2.5-7b as free translation channels.

Key Highlights

  • Added GLM-4 Flash and Qwen2.5-7b free translation channels.
  • Interface optimization.

New Features

  • GLM-4 Flash support
  • Qwen2.5-7b support

Full Release Notes

> 预打包版仅适用于Windows10/11，MacOS和Linux请源码部署
> MacOS/Linux升级：重新拉取源码覆盖，然后执行
>  `pip3 install --upgrade openai-whisper elevenlabs` 
>  `pip3 install --no-deps  --force-reinstall "faster-whisper @ https://github.com/SYSTRAN/faster-whisper/archive/refs/heads/master.tar.gz"`

## ChangeLogs

-  翻译渠道增加 `glm-4-flas` `qwen2.5-7b` 免费渠道
- 优化界面


## Win v3.47 完整包下载

> 如果未安装过旧版本，请在此下载完整版，如需cuda加速，需有英伟达显卡并且安装cuda12.x及cudnn9

百度网盘下载地址(含tiny/medium模型):   https://pan.baidu.com/s/1wuRnZPiTu7LmsddjJtYE9w?pwd=7v5r

GitHub下载地址(仅含tiny模型):  https://github.com/jianchang512/pyvideotrans/releases/download/v3.47/win-videotrans-v3.47-tiny.7z

 

## v3.47 补丁包190MB

> 如果已安装过3.x版本，可下载补丁包后解压在sp.exe所在目录，覆盖已有sp.exe和文件夹

百度网盘下载地址:   https://pan.baidu.com/s/12RHtjhHlZvyP4Ted1JiLFw?pwd=vfsx

GitHub地址: https://github.com/jianchang512/pyvideotrans/releases/download/v3.47/win-PatchUpdate-3.47.7z


> 若补丁覆盖后打开提示`需下载完整包`，请升级显卡驱动、升级cuda到12.x、升级cudnn到cudnn9，并重新下载完整包



----

### 所有模型下载地址

为避免压缩包体积过大，预打包版只内置最小模型 tiny，识别效果不佳，效果更好的模型请点击下载 ，建议至少使用medium模型，推荐large-v2

https://github.com/jianchang512/stt/releases/tag/0.0