Microsoft releases VibeVoice-ASR, an open speech-to-text model
1–2 of 2 posts
Re: Microsoft releases VibeVoice-ASR, an open speech-to-text model
#2VibeVoice-ASR is a unified speech-to-text model designed to handle 60-minute long-form audio in a single pass, generating structured transcriptions containing Who (Speaker), When (Timestamps), and What (Content), with support for Customized Hotwords.