After months of vibe-coding, I found myself not committing to any speech to text app.<p>Mostly because I didn't <i>trust</i> them:<p>I wanted something that ran locally, was open-source, and wasn't trying to squeeze me for a subscription for a trivial wrapper around a plethora of models.<p>There are some (fantastic new models)[<a href="https://huggingface.co/spaces/hf-audio/open_asr_leaderboard" rel="nofollow">https://huggingface.co/spaces/hf-audio/open_asr_leaderboard</a>] coming out all the time, this is a thin wrapper so PR a model that you prefer and we can keep adding them to the list.