@simon Do you know how this compares to whisper.cpp (which also uses the GPU on Macs)?
@saurabhs anecdotally it sounds like it’s a lot faster: https://twitter.com/awnihannun/status/1822744609241682077 says
“distil-large-v3 runs 40X faster than realtime on my M1 Max (transcribes 12 minutes in 18 seconds)”
Gregory's Server
@saurabhs anecdotally it sounds like it’s a lot faster: https://twitter.com/awnihannun/status/1822744609241682077 says
“distil-large-v3 runs 40X faster than realtime on my M1 Max (transcribes 12 minutes in 18 seconds)”