netease-youdao/Confucius4-R2T2 — new model trending #28 on Hugging Face
NetEase Youdao releases Confucius4-R2T2, a true streaming speech recognition model built on Qwen3-ASR with 200-600 ms latency and append-only output.
3
1 stories, newest first · one card per story
NetEase Youdao releases Confucius4-R2T2, a true streaming speech recognition model built on Qwen3-ASR with 200-600 ms latency and append-only output.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views