--- base_model: netease-youdao/Confucius4-R2T2 base_model_relation: quantized library_name: audio.cpp pipeline_tag: automatic-speech-recognition license: other license_name: netease-youdao-model-use-license license_link: https://github.com/netease-youdao/Confucius4-R2T2/blob/master/MODEL_LICENSE language: - zh - en - yue - ar - de - fr - es - pt - id - it - ko - ru - th - vi - ja - tr - hi - ms - nl - sv - da - fi - pl - cs - fil - fa - el - hu - mk - ro tags: - gguf - asr - automatic-speech-recognition - streaming - real-time - low-latency - quantized - qwen3-asr - confucius4 - r2t2 - audio.cpp --- # Confucius4-R2T2 — GGUF (audio.cpp) GGUF conversions of **NetEase Youdao Confucius4-R2T2**, a low-latency, append-only streaming ASR model (a Qwen3-ASR-1.7B fine-tune with Longest Stable Prefix decoding), ready to run with [audio.cpp](https://github.com/audio-cpp/audio.cpp) — no Python, no PyTorch, local inference on Metal / CUDA / CPU. * Original model: [netease-youdao/Confucius4-R2T2](https://huggingface.co/netease-youdao/Confucius4-R2T2) · [source code](https://github.com/netease-youdao/Confucius4-R2T2) · [demo](https://r2t2.youdao.com/demo) * Runtime: [audio.cpp](https://github.com/audio-cpp/audio.cpp) (`ggml`), family `r2t2_asr` ## Files | File | Quantization | Size | Notes | |---|---|---:|---| | `r2t2-q8_0.gguf` | Q8_0 | 2.31 GiB | Recommended: smallest, no measurable quality loss on the verification set | | `r2t2-f16.gguf` | F16 | 3.81 GiB | Maximum fidelity | Both files are **self-contained**: the tokenizer, processor config, generation config, chat template and the audio.cpp model spec are embedded, so the runtime needs nothing but the binary and the single `.gguf` (the embedded files are unpacked into a temporary directory at load time). Precision policy: **Q8_0 and higher are supported**. 4-bit and 5-bit quantizations (legacy and k-quant) are rejected at load time with an actionable error, because this graph's kernels are not validated below Q8_0 and otherwise decode to empty text. SHA-256: ``` 2f2896fb93fcb6cc95995e6c8aba22b2f68a714daab91a5be7890b3d177710cd r2t2-q8_0.gguf 4ec1a57adf0ef09b99850eb87aeb816068fcf8ea72e11a1a58b15a4faea388a4 r2t2-f16.gguf ``` ## Usage ### Install ```bash # via the audio.cpp model manager python3 tools/model_manager_v2.py install r2t2_asr_q8_0 # or r2t2_asr_f16 # or directly hf download davidxifeng/Confucius4-R2T2-gguf r2t2-q8_0.gguf \ --local-dir models/Confucius4-R2T2-GGUF ``` ### Offline transcription ```bash audiocpp_cli --task asr --family r2t2_asr \ --model models/Confucius4-R2T2-GGUF/r2t2-q8_0.gguf \ --backend metal --audio speech_16k.wav --text-out transcript.txt ``` ### Streaming (real-time, append-only) ```bash audiocpp_cli --task asr --mode streaming --family r2t2_asr \ --model models/Confucius4-R2T2-GGUF/r2t2-q8_0.gguf \ --backend metal --audio speech_16k.wav \ --session-option r2t2_asr.chunk_size_ms=320 \ --text-out transcript.txt ``` Chunk sizes from 80 ms to 2 s are supported; 320 ms is a good default on Apple Silicon. `--audio -` streams raw 16 kHz mono PCM from stdin for live sources. Pass `--language Chinese` to skip language detection and `--text "hotword, term"` for a context/hotword prompt. ### Server ```json { "id": "r2t2-asr", "family": "r2t2_asr", "path": "models/Confucius4-R2T2-GGUF/r2t2-q8_0.gguf", "task": "asr", "mode": "streaming", "session_options": { "r2t2_asr.chunk_size_ms": "320" } } ``` ```bash curl http://127.0.0.1:8488/v1/audio/transcriptions -F model=r2t2-asr -F file=@speech.wav curl -N http://127.0.0.1:8488/v1/audio/transcriptions \ -F model=r2t2-asr -F stream=true -F file=@speech.wav # SSE transcript deltas ``` See `docs/models/r2t2.md` in audio.cpp for the full option reference, the LSP streaming contract, and GGUF details. ## Conversion recipe ```bash audiocpp_gguf \ --input /path/to/Confucius4-R2T2/model.safetensors \ --root /path/to/Confucius4-R2T2 \ --family r2t2_asr \ --output r2t2-q8_0.gguf \ --type q8_0 ``` No weight-name or head flags are needed: the checkpoint ties the LM head to the token embedding (`lm_head.weight` is absent) and the loader detects that. Quantization only; no other weight modification. ## Verification These conversions were checked against the official reference implementation (PyTorch + MPS, `R2T2ASRModel`) on the model's own test clip and on the audio.cpp English sample: | Checkpoint | Offline text | Committed stream | Final transcript | Per-chunk committed text | |---|---|---|---|---| | `r2t2-q8_0.gguf` | exact | exact | exact | 21/21 exact | | `r2t2-f16.gguf` | exact | exact | exact | 21/21 exact | "Exact" means character-identical to the reference, including the reference's own `language` metadata-fragment artifact in the committed stream. Offline throughput on an Apple M3 is roughly 8× real time (RTF ≈ 0.13) for Q8_0. ## Language support Optimized for Chinese and English, with support for Cantonese, Arabic, German, French, Spanish, Portuguese, Indonesian, Italian, Korean, Russian, Thai, Vietnamese, Japanese, Turkish, Hindi, Malay, Dutch, Swedish, Danish, Finnish, Polish, Czech, Filipino, Persian, Greek, Romanian, Hungarian and Macedonian. ## License and attribution This is a **quantized Derivative Work** of [NetEase Youdao Confucius4-R2T2](https://huggingface.co/netease-youdao/Confucius4-R2T2), distributed under the **NetEase Youdao Model Use License Agreement** — full text in [`LICENSE`](LICENSE) (English) and [`LICENSE_zh`](LICENSE_zh) (Chinese); see also [`NOTICE`](NOTICE). The source code of the original model is Apache-2.0, the model weights are not. Required statement (license section 4.1(a)): > 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. Key restrictions: a separate commercial license is required above 100 M monthly active users or RMB 1 B annual revenue (section 2.2); the model may not be used to improve other AI models except Confucius4-R2T2, its derivatives, or non-commercial models (section 3.4(c)); high-risk uses such as medical diagnosis, autonomous driving, military, critical-infrastructure control, large-scale biometric surveillance and automated decision-making are prohibited (section 4.2). No trademark rights are granted (section 5.2). ## Citation ```bibtex @misc{Confucius4-R2T2, title = {Confucius4-R2T2: A Low Latency and High Accuracy Real-Time Speech Recognition Model}, author = {NetEase Youdao}, year = {2026}, howpublished = {https://github.com/netease-youdao/Confucius4-R2T2} } ```