v0.5.2

EvolvingLMMs-Lab/Aero-1v0.5.2Dec 21, 2024by t41372

AI Summary

Reverted the default Automatic Speech Recognition (ASR) provider from `faster-whisper` back to `FunASR` to resolve compatibility issues with Nvidia GPU users lacking cudnn.

Key Highlights

  • Reverted default ASR provider to FunASR
  • Fixed issues for Nvidia GPU users without cudnn

Breaking Changes

  • Default ASR provider changed from `faster-whisper` to `FunASR`

Full Release Notes

# v0.5.2 patch

The default ASR provider was changed back to `FunASR`. It was mistakenly set to `faster-whisper` a while ago without notice, and it caused a lot of problems for people who use Nvidia GPU without the cudnn. This change was not intended and has now been reversed.

**Full Changelog**: https://github.com/t41372/Open-LLM-VTuber/compare/v0.5.1...v0.5.2