News for hackers. Stuff that matters.
Re:Universal Speech Model by razemio on Thursday March 30, 2023 @01:32AM (#35368478)
What fixed it for me was whisper + language tool. It produces very good results with almost no errors. Even if the audio quality is bad.
Re:Universal Speech Model by rendall on Thursday March 30, 2023 @01:49AM (#35368588)
Would you mind expanding on this? I'm curious about the "+ language tool" part. Which tool?
Re:Universal Speech Model by petemir on Thursday March 30, 2023 @02:09AM (#35368706)
Not op, but probably he literally meant LanguageTool [0], an open-source grammarly alternative.

[0] https://languagetool.org/

Re:Universal Speech Model by razemio on Thursday March 30, 2023 @05:50AM (#35370253)
Correct!
Re:Universal Speech Model by barrenko on Thursday March 30, 2023 @03:00AM (#35369087)
Even something like "spacy" can help with the grammar.