v2.0

zaidmukaddam/scirav2.0Mar 31, 2026by lipku

AI Summary

Major refactoring to a plugin-based architecture with code reorganization into the avatars directory.

Key Highlights

  • Moved code to avatars directory
  • Switched to plugin-based architecture for models and TTS
  • Added RTMP streaming output
  • Integrated common logic into BaseAvatar and BaseAsr
  • Added Aliyun QwenTTS integration

Breaking Changes

  • Architecture refactored to plugin-based system
  • Code structure reorganized into avatars directory

New Features

  • Aliyun QwenTTS integration
  • RTMP streaming output
  • Plugin-based model/TTS architecture

Full Release Notes

1,重构代码,数字人模型和音频特征代码移到avatars目录下
2,数字人模型、tts、传输方式改成plugin方式接入
3,传输方式整理成单独的类,放到streamout目录下,添加rtmp输出
4,数字人推理和回贴公共部分代码整合到BaseAvatar中,各模型只需要实现自己特有部分代码
5,音频特征的切分代码整合到BaseAsr中
6,tts添加阿里云qwentts