Starstruk Logo MarkStarstruk

v3.43

jianchang512/pyvideotransv3.43Jan 7, 2025by jianchang512

AI Summary

This update focuses on optimizing the GeminiAI speech recognition channel and refining the subtitle translation prompts to improve accuracy.

Key Highlights

  • Optimized GeminiAI speech recognition channel
  • Refined subtitle translation prompts
  • MacOS/Linux upgrade instructions provided

New Features

  • Optimization of GeminiAI channel

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

- 优化 语音识别GeminiAI渠道
- 优化字幕翻译提示词


## Win v3.43 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/1pieqgZKX48ELt88uwyO3ew?pwd=bx6z

GitHub下载地址(仅含tiny模型):  https://github.com/jianchang512/pyvideotrans/releases/download/v3.43/win-videotrans-v3.43-tiny.7z

 

## v3.43 补丁包190MB

> 如果已安装过2.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/1E-OcuS3p2p2TGpsJ1NhcdQ?pwd=c918

GitHub地址: https://github.com/jianchang512/pyvideotrans/releases/download/v3.43/win-PatchUpdate-3.43.7z


> 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


----

api.exe 下载，api.exe是用于通过http请求调用的文件，不可独立使用，需先下载完整包，然后下载api.exe和 sp.exe放在同一目录下
 
api.exe下载地址：https://github.com/jianchang512/pyvideotrans/releases/download/v3.36/api.exe


----

### 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