CONSONANCE.for your information
Monday, 5 October 2026frenvi

Being discussed

01 — multimodal 3 VOICES

NetEase Youdao open-sources Confucius4-R2T2 real-time streaming ASR

NetEase Youdao open-sourced Confucius4-R2T2, a 1.7-billion parameter real-time streaming automatic speech recognition model. The model combines one audio encoder with an LLM foundation, specifically built to handle incremental speech processing for voice agents.

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 ↗
↑