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 2B Streaming ASR Model Confucius R2T2(15 posts)→
More from Multimodal
- Runway-made looping video reimagines Ganesh Chaturthi's made-new-not-made-new theme — CurieuxExplorer · 2026-09-17
- Use Timer Nodes When Benchmarking Generation Speed, Console Times Lie — CurrentMine1423 · 2026-09-17
- Zing-0.5: 5B Real-Time World Model With Joint Keyboard-Text Control, $0.009 per Stream-Minute — Mingyang Chen · 2026-09-17
- Creative short film made with Seedance 2.5 shows cinematic crowd-freeze scene — SimplyAnnisa · 2026-09-17
- Generative AI short film submitted to Lumara Film Festival — Kyrannio · 2026-09-17
- Google releases Gemma 3n: 2GB RAM multimodal model, first sub-10B to top 1300 on LMArena — joemeno · 2026-09-17