Re:Universal Speech Model
by dontreact on Thursday March 30, 2023 @12:51AM
(#35368152)
If there is a better mode I can easily integrate using python I’m all ears. For what I’m building quality is most important
[ Parent
| on HN ]
Oh, Azure's speech recognition API beats it handily on English language. Both in accuracy and speed.
Another is Deepgram. Even this obscure vendor seems to be able to handle the samples I tried better than Whisper: https://picovoice.ai/platform/cat/
But yeah, go with Azure as your starting point. It is good and the price is likely acceptable unless you're transcribing all of youtube.
Umm I want to pay zero and run locally
Re:Universal Speech Model
by generalizations on Thursday March 30, 2023 @04:43PM
(#35378582)
If you use the large_v2 version of whisper, and give it a prompt to indicate what it's transcribing, it can do extremely well. But do use the prompt feature.