CONSONANCE.for your information
Monday, 5 October 2026frenvi

Being discussed

01 — multimodal 3 VOICES

NetEase Youdao open-sources Confucius4-R2T2 1.7B real-time streaming ASR model

NetEase Youdao has open-sourced Confucius4-R2T2, a 1.7B parameter real-time streaming ASR model built specifically for voice agents. The architecture combines a single audio encoder with an LLM foundation to handle both offline and streaming speech recognition. It processes speech incrementally while restricting agent actions to committed text to prevent state corruption.

3 independent accounts 12 posts 6 articles 331 interactions
@GithubProjects their topics on X ↗
@alex_prompter their topics on X ↗
@dani_avila7 their topics on X ↗
@rohanpaul_ai their topics on X ↗
@NetEaseYouDaoAI their topics on X ↗
↑