It's a young project opensourced two months ago. I used it mostly for MiniMax Music 3 and TTS. I checked the PRs and some ASR model implementations/improvements are from the official model authors (e.g., Mistral AI, Alibaba, IBM and Microsoft) so it should be more reliable.
https://github.com/0xShug0/audio.cpp
It's a young project opensourced two months ago. I used it mostly for MiniMax Music 3 and TTS. I checked the PRs and some ASR model implementations/improvements are from the official model authors (e.g., Mistral AI, Alibaba, IBM and Microsoft) so it should be more reliable.
https://github.com/0xShug0/audio.cpp