Starstruk Logo MarkStarstruk

v3.53

jianchang512/pyvideotransv3.53Feb 15, 2025by jianchang512

AI Summary

Enhanced Edge-TTS with minor language support and added a feature to export individual subtitle audio files.

Key Highlights

  • Added support for other minor languages in the Edge-TTS channel.
  • Added option to keep individual subtitle audio files in the target folder.

New Features

  • Multi-language Edge-TTS support
  • Save individual subtitle audio files

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"`

## Change

- Fix: #738 
- Fix: `批量为字幕配音` 界面 Edge-tts 渠道增加其他小语种语言支持
- Fix: 调整 AI 翻译字幕时默认提示词
- Fix: openai 语音识别接口兼容第三方
- Feat: 高级选项中增加`保留每条字幕音频`选项，选中后将在目标文件夹内生成每条字幕对应的配音mp3 #731 


## Win v3.53 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/1JVM5SDyg7sMlcSyEfM9-Zw?pwd=bxtm

GitHub地址: https://github.com/jianchang512/pyvideotrans/releases/download/v3.53/win-videotrans-v3.53-tiny.7z

 

## v3.55 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/1cG6M-mhy-IvS4bzG3WdQCg?pwd=hvig

GitHub地址: https://github.com/jianchang512/pyvideotrans/releases/download/v3.53/win-PatchUpdate-3.55.7z


> 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