hugpadhugpad

microsoft / VibeVoice-ASR

Audio8.7B702.9K1.3KUpdated Jan 27, 2026
Hugging Face

Downloads

702.9K

Likes

1.3K

Last updated

Jan 27, 2026

License

mit

VibeVoice-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 and over 50 languages.

Tasks & library

  • automatic speech recognition
  • transformers

Tags

  • transformers
  • vibevoice
  • ASR
  • Transcriptoin
  • Diarization
  • Speech-to-Text

Technical specifications

Parameters8.7B
Librarytransformers
Languages51 languages
Licensemit