logoalt Hacker News

steinvakt2 • today at 1:36 PM • 1 reply • view on HN

Any way to use this for speech-to-text? To gain faster whisper inference for instance, without losing accuracy?

Replies

anerli • today at 5:52 PM

Yes :) same concept could apply there. If it's something you're interested in feel free to open an issue in our GitHub!