493
submitted 1 year ago by neme@lemm.ee to c/opensource@programming.dev
you are viewing a single comment's thread
view the rest of the comments
[-] themeatbridge@lemmy.world 2 points 1 year ago

That would depend on the LLM and the data used to train it.

[-] Aatube@kbin.melroy.org 3 points 1 year ago

IIRC you can't use LLMs for this.

[-] themeatbridge@lemmy.world 1 points 1 year ago

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..."

[-] kautau@lemmy.world 4 points 1 year ago* (last edited 1 year ago)

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

[-] themeatbridge@lemmy.world 1 points 1 year ago

That makes sense.

this post was submitted on 09 Jan 2025
493 points (99.0% liked)

Opensource

5053 readers
380 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 2 years ago
MODERATORS