v0.5.2
andrewyng/aisuitev0.5.2Dec 21, 2024by t41372
AI Summary
A patch release that reverts the default Automatic Speech Recognition (ASR) provider back to FunASR from faster-whisper to resolve compatibility issues with Nvidia GPU users lacking cuDNN.
Key Highlights
- Default ASR provider reverted to FunASR.
- Fixes Nvidia GPU compatibility issues related to missing cuDNN.
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