| --- |
| license: other |
| license_name: confucius4-r2t2-model-license |
| license_link: https://github.com/netease-youdao/Confucius4-R2T2/blob/main/MODEL_LICENSE |
| tags: |
| - mlx |
| - speech-to-text |
| - asr |
| - stt |
| - streaming |
| - mlx-audio |
| library_name: mlx-audio |
| base_model: netease-youdao/Confucius4-R2T2 |
| --- |
| |
| # Confucius4-R2T2, MLX 4-bit |
|
|
| [`netease-youdao/Confucius4-R2T2`](https://huggingface.co/netease-youdao/Confucius4-R2T2) |
| converted to MLX and quantised to 4 bits (group size 64, affine), for Apple |
| Silicon. 4.09 GB of bfloat16 becomes 1.5 GB. |
|
|
| Converted with `mlx-audio` 0.3.1: |
|
|
| ```bash |
| python -m mlx_audio.convert --hf-path netease-youdao/Confucius4-R2T2 \ |
| --mlx-path Confucius4-R2T2-mlx-4bit \ |
| -q --q-group-size 64 --q-bits 4 --model-domain stt |
| ``` |
|
|
| The architecture is unchanged — `Qwen3ASRForConditionalGeneration`, the same one |
| `Qwen/Qwen3-ASR-1.7B` uses — so it loads through existing Qwen3-ASR paths in |
| both `mlx-audio` and `mlx-audio-swift` with no custom code. |
|
|
| ## Use |
|
|
| ```python |
| from mlx_audio.stt.utils import load_model, load_audio |
| model = load_model("selcukkubur/Confucius4-R2T2-mlx-4bit") |
| print(model.generate(load_audio("audio.wav")).text) |
| ``` |
|
|
| ## Notice |
|
|
| 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. |
|
|
| This is a quantisation of NetEase Youdao's Confucius4-R2T2 and is governed by |
| the original [MODEL_LICENSE](https://github.com/netease-youdao/Confucius4-R2T2/blob/main/MODEL_LICENSE). |
| That licence is royalty-free for most users but requires a separate licence from |
| NetEase Youdao above 100 million monthly active users or RMB 1 billion in annual |
| revenue, and prohibits use in the high-risk scenarios it lists. Read it before |
| use. |
|
|
