Microsoft releases VibeVoice-ASR, an open speech-to-text model

Microsoft releases VibeVoice-ASR, an open speech-to-text model(github.com)

3 points by putlake 114 days ago | 1 comment

putlake 114 days ago |

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.

putlake 114 days ago |

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.