maco on 2026-04-28 14:54:34
https://github.com/microsoft/VibeVoice
MICROSOFT OPEN SOURCED A 7B PARAMETER MODEL THAT TRANSCRIBES 60 MINUTES OF AUDIO IN A SINGLE PASS
and it's completely free
VIBEVOICE ASR no chunking, no context loss, full speaker diarization baked in
not just speech to text..not a basic wrapper
who spoke, when they spoke,… pic.twitter.com/x9Dft0B1OF
— Rahul (@sairahul1)
April 27, 2026