v3.00
jianchang512/pyvideotransv3.00Nov 3, 2024by jianchang512
AI Summary
Introduces version 3.0 with a Windows-specific pre-packaged build and new AI translation capabilities.
Key Highlights
- Windows 10/11 specific pre-packaged version available
- Three-step reflection method for AI translation (online models only)
- Fix for DeepL auto-detection of pronunciation language
New Features
- Three-step reflection AI translation
- DeepL auto pronunciation language fix
Full Release Notes
> 预打包版仅适用于Windows10/11,MacOS和Linux请源码部署 - Feat: AI翻译时,并且选中了发送完整字幕,将启用三步反思法翻译,效果可能更好,但仅限在线大模型,不支持本地模型(显然效果会很差) - Fix: 修复Deepl选择发音语言自动时bug ## v3.11 完整包下载3.4G(含tiny/medium模型) > 如果未安装过旧版本,请在此下载完整版 百度网盘: https://pan.baidu.com/s/1FTKHFM7l9ndbTmX0Z2uovg?pwd=9dm8 Huggingface(墙外): https://huggingface.co/spaces/mortimerme/s4/resolve/main/windows-videotrans-v3.11.7z?download=true ## v3.14补丁包84MB > 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 GitHub: https://github.com/jianchang512/pyvideotrans/releases/download/v3.00/win-PatchUpdate-3.14.7z 百度网盘: https://pan.baidu.com/s/1a-SlQZkDpT8gaXJs_IglOA?pwd=rvgu ---- > 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/v3.00/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 https://github.com/jianchang512/stt/releases/tag/0.0