NetEase Youdao's Confucius4-R2T2 streaming ASR model trends on Hugging Face

netease-youdao · hf · 2026-09-20

NetEase Youdao's Confucius4-R2T2 automatic speech recognition model is trending on Hugging Face. Built on the Qwen3-ASR architecture, it targets streaming, real-time, low-latency transcription, ships in safetensors format, and supports vLLM inference.

Related event: NetEase Youdao Open-Sources Streaming ASR Model Confucius4-R2T2(3 posts)→

Original post →

More from Models

Models channel →