#multilingual

Model deep dive·Oct 8, 2026

Run Confucius4-R2T2 for Append-Only Real-Time Speech Recognition

NetEase Youdao's streaming ASR model built on Qwen3-ASR: transcript text never gets rewritten, with 80 ms to 2 s chunks. Setup, code and caveats.

netease-youdao/Confucius4-R2T2

Model deep dive·Oct 8, 2026

Laya: Typed Routing and Triage Decisions in One ~33 ms Pass

Laya answers typed questions about text with probabilities instead of generated text. It covers 100+ languages and is Apache 2.0. Fit temperatures before trusting the probabilities.

convaiinnovations/laya