v4.09

clusterzx/paperless-aiv4.09Aug 7, 2026by jianchang512

Upgrading?

AI Summary

This release focuses on enhancing speech recognition and translation capabilities on Windows, introducing new AI models for TTS and ASR, and fixing critical bugs in the Whisper engine.

Key Highlights

  • Added support for speaker diarization (Moss-Transcribe-Diarize) for audio/video up to 90 minutes.
  • Introduced new TTS model 'higgs-audio-v3-tts-4b' and updated F5-TTS language support.
  • Fixed Faster_whisper_xxl.exe errors and restored local subtitle import functionality.
  • Added new HuggingFace ASR models including Audio8/ARK-ASR-0.6B and granite-speech-4.1-2b.

New Features

  • Support for index-tts 2.5
  • Speaker diarization support
  • New ASR models (Audio8/ARK-ASR-0.6B, ibm-granite/granite-speech-4.1-2b)
  • New TTS model (higgs-audio-v3-tts-4b)
  • F5-TTS language support (Vietnamese, Turkish)
  • Auto-fallback to local M2M100 model when Microsoft translation fails

Full Release Notes

## v4.09 Change log

> MacOX / Linux 请使用源码部署


**v4.09更新日志**

- 支持 index-tts 2.5 
- 修复 Faster_whisper_xxl.exe 报错
- 优化字幕翻译提示词
- 恢复导入本地源语言字幕按钮,仅单视频模式下生效
- 微软翻译已无法使用,报错时自动使用本地模型`M2M100(内置)`替换
- 语音识别 增加`Moss-Transcribe-Diarize`模型,90分钟内音视频支持直接返回说话人
- 语音识别 Huggingface_ASR渠道 增加模型`Audio8/ARK-ASR-0.6B` `ibm-granite/granite-speech-4.1-2b`
- 配音渠道增加`higgs-audio-v3-tts-4b`模型,CUDA加速需10G+显存,CPU运行需20G+内存
- F5-TTS 增加 越南语、土耳其语支持
- 修复其他已知bug



----

### v4.09 完整包下载(2.7G)

- 百度网盘地址: https://pan.baidu.com/s/1deSACf5Wmy34Ua8hzgDQVw?pwd=1234
- huggingface.co:  https://huggingface.co/mortimerme/repocollect/resolve/main/win-pyvideotrans-v4.09-0816.7z?download=true


### v4.09 补丁包下载(300MB)

> 补丁包不可单独使用,仅用于覆盖旧包, 覆盖后如果闪退或报错,请下载完整包。

- 百度网盘地址: https://pan.baidu.com/s/1GPBXPSSbNdUk9hUKIPjQZQ?pwd=1234
- huggingface.co: https://huggingface.co/mortimerme/repocollect/resolve/main/win-PatchUpdate-v4.09-0816.7z?download=true


**Full Changelog**: https://github.com/jianchang512/pyvideotrans/compare/v4.08...v4.09

Related Repositories