v3.64

jianchang512/pyvideotransv3.64Mar 7, 2025by jianchang512

AI Summary

Fixed Edge-TTS 403 error issues and added configuration controls for speech recognition duration.

Key Highlights

Added pause/wait mechanism after Edge-TTS to reduce 403 errors.
Added controls for minimum and maximum speech duration in faster-whisper and GeminiAI settings.

New Features

Edge-TTS pause feature
Duration controls for STT

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: #671 
- Fix: edge-tts 渠道每次配音后增加暂停等待，以尽量避免403错误，菜单-工具-选项-高级选项--配音后暂停填写大于5的数值
- Fix: faster-whisper/GeminiAI作为语音识别渠道时，可通过 菜单-工具-高级选项-faster/openai--最短语音持续时间/最大语音时间 来调整语音识别出的字幕时长


## Win v3.65 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/1X-UfNnOz8SgNn6qlyNn7rA?pwd=2s7d

GitHub地址: https://github.com/jianchang512/pyvideotrans/releases/download/v3.64/win-videotrans-v3.65-tiny.7z

 

## v3.65 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/1AFcVVL9n5TfpgiQPfOMPiw?pwd=817i

GitHub地址: https://github.com/jianchang512/pyvideotrans/releases/download/v3.64/win-PatchUpdate-3.65.7z


> 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