News for hackers. Stuff that matters.
Re:Model Distillation in the API by ben_w on Thursday October 31, 2024 @03:09PM (#42010329)
> - offers unrivaled voice-to-text models at different sizes (Whisper).

It may be (close to) the best, but Whisper is nowhere near good enough.

So, if you're got a great idea for how to massively improve on that (I don't), there's a business opportunity there.

There are no comments on this comment yet.