Automatic Speech Recognition
MLX
Safetensors
granite_speech
mlx-audio
speech-to-text
speech-translation
granite
granite-speech
autoregressive
quantized
4-bit precision
Instructions to use divydeep/granite-speech-4.1-2b-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use divydeep/granite-speech-4.1-2b-mlx-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir granite-speech-4.1-2b-mlx-4bit divydeep/granite-speech-4.1-2b-mlx-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "feature_extractor_type": "GraniteSpeechFeatureExtractor", | |
| "melspec_kwargs": { | |
| "hop_length": 160, | |
| "n_fft": 512, | |
| "n_mels": 80, | |
| "sample_rate": 16000, | |
| "win_length": 400 | |
| }, | |
| "processor_class": "GraniteSpeechProcessor", | |
| "projector_downsample_rate": 5, | |
| "projector_window_size": 15, | |
| "sampling_rate": 16000 | |
| } | |