Confucius4-R2T2 published
The story so far
NetEase Youdao has released the Confucius4-R2T2 stable prefix streaming speech recognition model for real-time transcription, which converts full-context ASR models into streaming models through post-training without architectural modifications. The model is based on Qwen3-ASR-1.7B and achieves near-offline recognition accuracy and low transmission latency, supporting configurable streaming block sizes and demonstrating promising cross-language generalization capabilities. The model and implementation have been publicly released and can be accessed via Hugging Face, GitHub, and an online demo.
AI-written from the reports · Updated 9 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersConfucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription
Confucius4-R2T2 is a stable prefix streaming speech recognition model for real-time applications, which converts a full context ASR model into a streaming model through post-training without architecture modification. Built based on Qwen3-ASR-1.7B, R2T2 achieves near-offline recognition accuracy and low transmission delay, supports configurable streaming block sizes, and demonstrates promising cross-lingual generalization capabilities. This model and implementation have been publicly released.