Automatic Speech Recognition
MLX
meralion2
meralion
speech
audio
speech-to-text
apple-silicon
quantized
2bit
rotorquant
gemma-2
whisper
sea-lion
custom_code
2-bit
Instructions to use majentik/MERaLiON-2-10B-RotorQuant-MLX-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use majentik/MERaLiON-2-10B-RotorQuant-MLX-2bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir MERaLiON-2-10B-RotorQuant-MLX-2bit majentik/MERaLiON-2-10B-RotorQuant-MLX-2bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_meralion2.MERaLiON2Processor" | |
| }, | |
| "chunk_length": 30, | |
| "dither": 0.0, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 128, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "n_samples": 480000, | |
| "nb_max_frames": 3000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "processor_class": "MERaLiON2Processor", | |
| "return_attention_mask": false, | |
| "sampling_rate": 16000 | |
| } | |