Confucius4-R2T2 — MLX, bf16
netease-youdao/Confucius4-R2T2 — NetEase
Youdao's low-latency, append-only streaming ASR fine-tune of Qwen3-ASR-1.7B — converted to MLX:
no quantisation — the reference tier (4.08 GB).
Converted with the mlx_audio.convert CLI (xocialize/mlx-audio fork @ 1792021, mlx 0.32.2), on
the GPU stream of an Apple M5 Max — MLX quantisation is device-dependent, so the device is recorded:
python -m mlx_audio.convert --hf-path netease-youdao/Confucius4-R2T2 \
--mlx-path Confucius4-R2T2-bf16 --model-domain stt
The architecture is qwen3_asr, unchanged from Qwen/Qwen3-ASR-1.7B, so the weights load through
the existing Qwen3-ASR paths of mlx-audio (Python) and mlx-audio-swift, and through
qwen3-asr-mlx-swift, whose R2T2 loop and
MLXEngine stt package (mlx-r2t2-stt-swift)
are what this repo exists for.
Use
from mlx_audio.stt.utils import load_model, load_audio
model = load_model("mlx-community/Confucius4-R2T2-bf16")
print(model.generate(load_audio("audio.wav"), language="English").text)
Streaming (the stable-prefix protocol the model was trained for) needs the R2T2 loop: 160 ms chunks,
re-feed the audio window with the committed text as the prompt, cut the output at |, roll back one
token, commit the rest. See the Swift package above or netease-youdao/Confucius4-R2T2.
Licence
The weights are governed by the NetEase Youdao Model Use License Agreement (LICENSE; the
Chinese text in MODEL_LICENSE_zh prevails). It is royalty-free, including commercial use, but
requires a separate licence from NetEase Youdao above 100 million monthly active users or RMB 1
billion annual revenue (§2.2), forbids using the model to improve other commercial AI models
(§3.4 c) and the high-risk uses it lists (§4.2), and binds downstream recipients to the same terms
(§3.4 a). Read it before use.
Any modifications made to the original model in this Derivative Work are not endorsed, warranted, or guaranteed by the original right-holder of the original model, and the original right-holder disclaims all liability related to this Derivative Work.