logoalt Hacker News

garblegarbleyesterday at 5:05 PM3 repliesview on HN

I have tried everything (that will run on a 12GB RTX 4070) and I have yet to find anything with better accuracy than Whisper V2 Large for my dataset (discord audio from TTRPG sessions, isolated per-speaker, mostly non-American accents)


Replies

Ey7NFZ3P0nzAeyesterday at 9:21 PM

Voxtral to me what better

xd1936yesterday at 5:15 PM

Same, for my English-only podcast

modelessyesterday at 6:33 PM

Not v3?