[qingcharles]

I used to work correcting AI transcriptions.

There is only so much AI can do because it currently lacks in certain domain knowledge.

The worst one I ever had to fix was ESPN captions of commentary for some indoor motorcross thing with dirt bikes going around a track. First, the motorbike noise, but secondly, the commentators were using the (well known to fans) nicknames for all the riders, which the AI had no idea how to transcribe, no idea who they were, and were almost impossible for me to even Google.

[simonw]

Whisper has a feature where you can provide it with a text prompt before it starts transcribing to clue it up to additional vocabulary that it may need to know.