| --- |
| license: apache-2.0 |
| library_name: mlx |
| pipeline_tag: automatic-speech-recognition |
| base_model: |
| - XiaomiMiMo/MiMo-V2.5-ASR |
| tags: |
| - mlx |
| - apple-silicon |
| - automatic-speech-recognition |
| - speech-recognition |
| - mimo |
| language: |
| - zh |
| - en |
| --- |
| |
| Part of the [MiMo V2.5 ASR MLX](https://huggingface.co/collections/mlx-community/mimo-v25-asr-6a02cb99466d6a36475a4d70) collection. |
|
|
| # MiMo-V2.5-ASR-MLX-4bit (MLX) |
|
|
| Apple MLX weights for [XiaomiMiMo/MiMo-V2.5-ASR](https://github.com/XiaomiMiMo/MiMo-V2.5-ASR), converted for local ASR on Apple Silicon. |
|
|
| ## TL;DR |
|
|
| | | | |
| |---|---| |
| | **Variant** | 4-bit | |
| | **Best for** | smallest checkpoint | |
| | **Official code** | [`XiaomiMiMo/MiMo-V2.5-ASR`](https://github.com/XiaomiMiMo/MiMo-V2.5-ASR) | |
| | **MLX helper** | [`ailuntx/MiMo-V2.5-ASR-MLX`](https://github.com/ailuntx/MiMo-V2.5-ASR-MLX) | |
| | **MLX runtime dependency** | [`ailuntx/mlx-audio`](https://github.com/ailuntx/mlx-audio) | |
| | **Audio tokenizer** | [`mlx-community/MiMo-Audio-Tokenizer`](https://huggingface.co/mlx-community/MiMo-Audio-Tokenizer) | |
| | **Hardware** | Apple Silicon recommended; HF Spaces CPU fallback is only a load smoke test | |
|
|
| ## Quick Start |
|
|
| ```bash |
| git clone https://github.com/ailuntx/MiMo-V2.5-ASR-MLX.git |
| cd MiMo-V2.5-ASR-MLX |
| python -m venv .venv |
| .venv/bin/pip install git+https://github.com/ailuntx/mlx-audio.git |
| |
| hf download mlx-community/MiMo-Audio-Tokenizer --local-dir ./models/MiMo-Audio-Tokenizer |
| hf download mlx-community/MiMo-V2.5-ASR-MLX-4bit --local-dir ./models/MiMo-V2.5-ASR-MLX-4bit |
| |
| .venv/bin/python run_mimo_asr_mlx.py \ |
| --model ./models/MiMo-V2.5-ASR-MLX-4bit \ |
| --audio path/to/audio.wav |
| ``` |
|
|
| ## Variants |
|
|
| | Variant | Best for | |
| |---|---| |
| | [`MiMo-V2.5-ASR-MLX`](https://huggingface.co/mlx-community/MiMo-V2.5-ASR-MLX) | default entry | |
| | [`MiMo-V2.5-ASR-MLX-fp32`](https://huggingface.co/mlx-community/MiMo-V2.5-ASR-MLX-fp32) | high-precision baseline | |
| | [`MiMo-V2.5-ASR-MLX-bf16`](https://huggingface.co/mlx-community/MiMo-V2.5-ASR-MLX-bf16) | high-quality Apple Silicon use | |
| | [`MiMo-V2.5-ASR-MLX-8bit`](https://huggingface.co/mlx-community/MiMo-V2.5-ASR-MLX-8bit) | smaller local checkpoint | |
| | [`MiMo-V2.5-ASR-MLX-4bit`](https://huggingface.co/mlx-community/MiMo-V2.5-ASR-MLX-4bit) | smallest checkpoint | |
|
|
| ## Layout |
|
|
| ```text |
| MiMo-V2.5-ASR-MLX-4bit/ |
| ├── config.json |
| ├── model.safetensors / shards |
| ├── tokenizer files |
| └── mlx_manifest.json |
| ``` |
|
|
| ## Conversion Notes |
|
|
| | Component | Source | MLX handling | |
| |---|---|---| |
| | ASR model | `XiaomiMiMo/MiMo-V2.5-ASR` | converted to MLX weights | |
| | audio tokenizer | `mlx-community/MiMo-Audio-Tokenizer` | downloaded separately and passed to the runtime | |
| | helper script | `ailuntx/MiMo-V2.5-ASR-MLX` | wraps `mlx-audio` loading/generation | |
|
|
| ## Validation |
|
|
| Local Apple Silicon is the intended runtime. The HF Space can start and load the model on Linux CPU fallback, but full ASR on `cpu-basic` can exceed request timeouts. |
|
|
| ## License |
|
|
| License follows the upstream MiMo release. |
|
|
| ## Citation |
|
|
| ```bibtex |
| @misc{mimo-v25-asr-mlx, |
| title = {MiMo-V2.5-ASR-MLX: Apple MLX port of MiMo-V2.5-ASR}, |
| author = {ailuntx}, |
| year = {2026}, |
| url = {https://github.com/ailuntx/MiMo-V2.5-ASR-MLX}, |
| } |
| |
| @misc{xiaomi2026mimov25asr, |
| title = {MiMo-V2.5-ASR}, |
| author = {{Xiaomi MiMo Team}}, |
| year = {2026}, |
| url = {https://github.com/XiaomiMiMo/MiMo-V2.5-ASR}, |
| } |
| ``` |
|
|
