NetEase Youdao open-sources Confucius R2T2, a 2B real-time speech model with tunable latency
dr_cintas · x · 2026-09-17
NetEase Youdao released Confucius R2T2, an open-source 2B-parameter speech model that transcribes in real time with near-offline accuracy. Its streaming decoding chunks are tunable from 80ms to 2s, letting developers set their own latency-accuracy trade-off. Fully free to download and run.
Related event: NetEase Youdao Open-Sources Streaming ASR Model Confucius4-R2T2(21 posts)→
More from Multimodal
- Midjourney dual --sref combo produces medieval woodcut cat knight art — sergeantsref · 2026-11-02
- Fluffy AI-generated character designs: fox girl, alien bug and cat photographer — OVolosin82152 · 2026-11-02
- Fable 5.5 reportedly one-shots animation in pure code as Anthropic's coding bet pays off — Hesamation · 2026-11-02
- FlowHMR gets 5x faster, demoing an LLM agent pipeline from video to photoreal mocap — camenduru · 2026-11-02
- Retro 1973 music video "Rock is Dead" by TECHHALLA showcases startlingly realistic AI generation — Mother-Pear-2392 · 2026-11-02
- Weekend splatting with COLMAP and Lichtfeld — janusch_patas · 2026-11-02