Automatic Speech Recognition
MLX
Safetensors
moss_transcribe_diarize
speaker-diarization
audio
moss
custom_code
Instructions to use vanch007/mlx-MOSS-Transcribe-Diarize with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use vanch007/mlx-MOSS-Transcribe-Diarize with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download vanch007/mlx-MOSS-Transcribe-Diarize --local-dir mlx-MOSS-Transcribe-Diarize
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download preprocessor_config.json from vanch007/mlx-MOSS-Transcribe-Diarize: direct link, hf CLI and curl.
- Browser
- Download file 315 Bytes
-
https://huggingface.co/vanch007/mlx-MOSS-Transcribe-Diarize/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://vanch007/mlx-MOSS-Transcribe-Diarize/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/vanch007/mlx-MOSS-Transcribe-Diarize/resolve/main/preprocessor_config.json
315 Bytes
| { | |
| "chunk_length": 30, | |
| "dither": 0.0, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 80, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "n_samples": 480000, | |
| "nb_max_frames": 3000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": false, | |
| "sampling_rate": 16000 | |
| } | |