Universal Speech Model

Re:Universal Speech Model by 101008 on Wednesday March 29, 2023 @10:31PM (#35367115)

Whisper is great. You can get faster results running the tiny model. I used it for podcast transcription and it is much faster and the quality is not worse than the medium model - there are some podcast episodes that the transcription is the same.

[ Parent | on HN ]

Re:Universal Speech Model by alach11 on Wednesday March 29, 2023 @10:48PM (#35367253)

If speed is important, you're much better off using a larger model and whisper.cpp.

[ Parent | on HN ]

Re:Universal Speech Model by pantalaimon on Thursday March 30, 2023 @06:55AM (#35370746)

Wow thank you! That's a nice speedup indeed, with whisper I get

    33,53s user 2,05s system 443% cpu 8,023 total

with the 'tiny.en' model whereas whisper.cpp gives me

    22,71s user 0,12s system 745% cpu 3,062 total

with the 'base.en' model for a 15s audio clip on an i7-3770 (8 threads).

[ Parent | on HN ]

Re:Universal Speech Model by alach11 on Thursday March 30, 2023 @11:25AM (#35374153)

Awesome! Thanks for posting the stats.

In my workflows I've found rare but noticeable quality differences between the model sizes. So when practical I try to use the larger ones.

[ Parent | on HN ]