Benchmarking Top Open Source Speech Recognition Models: Whisper, Facebook wav2vec2, and Kaldi
What's this blog post about?
In this comparison of open-source ASR models, Kaldi performs poorly across all metrics and domains. Whisper outperforms wav2vec 2.0 in terms of accuracy but is significantly slower. The choice between these two options would depend on the specific needs of the user.
Company
Deepgram
Date published
Dec. 19, 2022
Author(s)
Andrew Seagraves
Word count
5472
Hacker News points
None found.
Language
English