tjongsma

Medium model output is nonsense for batched pipeline (for short 15s audio clips)

9

Like the title implies, when using the batched commits and using the medium model the model output is nonsense (empty, repeats the inital prompt or says 'I'm sorry'). I'm using...

Hi there, I've been using insanely-fast-whisper to try do some live streaming. I'm using this gist for reference: https://gist.github.com/Und3rf10w/a2561b569572677dd9c1f8db8e92fb25 Everything works fine for large-v3 (albeit somewhat slowly), but if I...

Strange results for short audio clips

8

Hi there, First off, amazing job on your paper/the model! It looks super promising. I'm working on a project where I'm attempting to do live streaming with Whisper. One of...