Damn! Thats awesome
Yeah, cant wait to try it. I have already moved coding to audio. I think in a year I'll 90% voice.
"OpenAI just released Whisper Turbo, a lightning-fast speech-to-text model with 809M parameters—8x faster than the large version and needing only 6GB of VRAM. Awni Hannun reports it can transcribe 12 minutes of audio in just 14 seconds on an M2 Ultra. "
So, this is local?
Yes. Whisper is completely local run.
That’s awesome How do I download and setup?