this post was submitted on 09 Jan 2025
420 points (98.8% liked)

Opensource

1615 readers
505 users here now

A community for discussion about open source software! Ask questions, share knowledge, share news, or post interesting stuff related to it!

CreditsIcon base by Lorc under CC BY 3.0 with modifications to add a gradient



founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 1 points 1 day ago (1 children)

I didn't read the article, but I would have assumed that the AI was using predictive text to guess at the next word. Speech recognition is already pretty good, but it often misses contextual cues that an LLM would be good at spotting. Like, "The famous French impressionist painter mayonnaise..."

[–] [email protected] 4 points 1 day ago* (last edited 1 day ago) (1 children)

Probably something like https://github.com/openai/whisper which isn’t an LLM, but is a different type of model dedicated to speech recognition

[–] [email protected] 1 points 1 day ago

That makes sense.