Confucius4-R2T22 min read
Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription
Streaming speech recognition is increasingly consumed by machines, such as translators and voice agents, that act on each token as it appears. A token that is later revised costs wasted work or a wrong action.
By Daniel Huang, Qi He, Shaoxiong Duan, Yingjie Li, Qiao Cheng, Yitao DuanarXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Nov 5, 2026.
Comments
Sign in to join the discussion.