Automatic Speech Recognition
MLX
Safetensors
Chinese
English
qwen2
asr
speech-recognition
mimo
4-bit precision
Instructions to use mlx-community/MiMo-V2.5-ASR-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/MiMo-V2.5-ASR-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir MiMo-V2.5-ASR-MLX-4bit mlx-community/MiMo-V2.5-ASR-MLX-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Point README.md to mlx-community tokenizer mirror
Browse files
README.md
CHANGED
|
@@ -106,8 +106,8 @@ The following repositories are MLX conversions derived from the official release
|
|
| 106 |
MLX conversion notes:
|
| 107 |
|
| 108 |
- Base model: `XiaomiMiMo/MiMo-V2.5-ASR`
|
| 109 |
-
- One-line MLX loading: `fromPretrained("mlx-community/MiMo-V2.5-ASR-MLX")` auto-resolves the
|
| 110 |
-
- Tokenizer resolution: automatic via `
|
| 111 |
- Conversion date: `2026-05-12`
|
| 112 |
- Local validation runtime: `mlx-audio-swift`
|
| 113 |
- Recommended default: `MiMo-V2.5-ASR-MLX`
|
|
|
|
| 106 |
MLX conversion notes:
|
| 107 |
|
| 108 |
- Base model: `XiaomiMiMo/MiMo-V2.5-ASR`
|
| 109 |
+
- One-line MLX loading: `fromPretrained("mlx-community/MiMo-V2.5-ASR-MLX")` auto-resolves the tokenizer mirror
|
| 110 |
+
- Tokenizer resolution: automatic via `mlx-community/MiMo-Audio-Tokenizer`
|
| 111 |
- Conversion date: `2026-05-12`
|
| 112 |
- Local validation runtime: `mlx-audio-swift`
|
| 113 |
- Recommended default: `MiMo-V2.5-ASR-MLX`
|