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

3 pointsby putlake6 เดือนที่ผ่านมา1 comments

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

https://github.com/microsoft/VibeVoice/blob/main/docs/vibevoice-asr.md

1 comments

putlake6 เดือนที่ผ่านมา

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.