Starstruk Logo MarkStarstruk

v3.99

thedotmack/claude-memv3.99Apr 14, 2026by jianchang512

AI Summary

This release focuses on upgrading audio processing models, optimizing caching strategies, and unifying settings across various TTS engines. It also introduces a debugging tool and removes deprecated model names.

Key Highlights

  • Upgraded noise reduction model to dpdfnet.
  • Added spleeter for voice and background separation.
  • Optimized caching strategy for TTS files.
  • Unified reference audio settings UI for multiple TTS engines.
  • Added _debug.exe for troubleshooting crashes.

Breaking Changes

  • Removed support for certain deprecated AI model names.

New Features

  • New noise reduction model (dpdfnet).
  • New source separation model (spleeter).
  • Enhanced caching strategy for repeated processing.
  • Unified reference audio settings interface.
  • Added _debug.exe debugging file.
  • Updated subtitle translation prompt terminology variable.

Full Release Notes

*v3.99 0508更新日志*

- 降噪模型改用 [dpdfnet](https://k2-fsa.github.io/sherpa/onnx/speech-enhancement/dpdfnet.html)
- 人声背景声分离模型增加 [spleeter](https://k2-fsa.github.io/sherpa/onnx/source-separation/models.html#spleeter)
- 优化缓存策略，以便尽量多使用配音缓存(未关闭软件并对同一文件反复处理时)
- 统一参考音频设置界面(F5-TTS/CosyVoice/Chatterbox/OmniVoice/Index-TTS/VoxCPM/Moss-nano)
- 增加 _debug.exe 调试文件，当出错但报错信息不明时，可使用该文件启动
- 优化一些默认设置项，移除已不再支持的某些AI模型名字
- 修改字幕翻译提示词中`术语表`嵌入变量





##  v3.99 完整包下载(2.5G)


百度网盘下载地址: https://pan.baidu.com/s/1HN3qVb5MMrEf8ukce6D-tA?pwd=1234

huggingface.co:  https://huggingface.co/mortimerme/repocollect/resolve/main/win-pyvideotrans-v3.99-0508.7z?download=true


<details>
<summary>v3.99 补丁包(300MB)</summary>

> 不可单独使用，仅用于覆盖旧包，与完整包区别是不含有`torch`模块
> 因torch从 2.5 升级到 2.7，补丁包不含有torch，直接下载覆盖补丁包可能导致无法cuda加速，建议下载完整包覆盖
> **覆盖后如果闪退，请下载完整包**

百度网盘下载地址: https://pan.baidu.com/s/1iLcbVLt_cSOYaMlCvgj1rw?pwd=1234

huggingface.co: https://huggingface.co/mortimerme/repocollect/resolve/main/win-PatchUpdate-v3.99-0508.7z?download=true

</details>