logoalt Hacker News

s3p • yesterday at 12:41 PM • 3 replies • view on HN

Is it even worth using apple's? Maybe they have improved it but when they first started using it to transcribe voice memos it was laughably bad (in my experience). I defaulted to whisper.cpp


Replies

solarkraft • yesterday at 5:16 PM

I used it a lot in my AI client before I finally got around to hacking a Deepgram API server into Handy: It sucks enough to give me a headache worrying about its unreliability in every given transcription.

They supposedly improved it on later Apple Intelligence enabled devices, but I don’t have one.

➕ show 1 reply
llimllib • yesterday at 1:27 PM

apple's is 5x faster than `large-v3-turbo` with whisper.cpp and in my test had somewhat worse performance, so it's a tradeoff

ChrisMarshallNY • yesterday at 2:24 PM

I suspect Apple's strengths are in multi-language support.

I use their on-device translation in my apps. Works pretty well. ChatGPT's context-aware translation is better, but it's not on-device.