Speech and audio·EASYHUB JOURNAL
NetEase Youdao open-sources R2T2 and T3PO for live transcription and simultaneous translation
What changed
NetEase Youdao has released Confucius4-R2T2 for true-streaming ASR and the 14B T3PO model for simultaneous text translation. R2T2 supports 80 ms to 2 s chunks and append-only transcripts, while T3PO makes incremental READ/WRITE decisions across selectable quality-latency modes. T3PO does not natively accept speech and must be cascaded with streaming ASR such as R2T2.
- Original title
- Confucius4-R2T2: A Low Latency and High Accuracy Real-Time Speech Recognition Model
- Source
- NetEase Youdao · github.com
- Topic
- Speech and audio
- Source month
- 2026-09
This is a concise EasyHub summary of the linked source, not the full report or original reporting. Availability and preview conditions are described in the summary and original.
Summary page published · Updated · Editorial information