Preprint
Sep 2026
VibeVoice-ASR-Streaming Technical Report
VibeVoice-ASR-Streaming is one of the first LLM-based end-to-end approaches to streaming speaker-attributed ASR, allowing the model to produce''who said what''as speech arrives, without a separate diarization stage.
Yu-Jie Tu, Zhiliang Peng, Jianwei Yu et al.
· 0 citations