Instructions to use cwkeam/mctc-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cwkeam/mctc-large with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import MCTCForCTC model = MCTCForCTC.from_pretrained("cwkeam/mctc-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from cwkeam/mctc-large: direct link, hf CLI and curl.
- Browser
- Download file 497 Bytes
-
https://huggingface.co/cwkeam/mctc-large/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://cwkeam/mctc-large/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/cwkeam/mctc-large/resolve/main/preprocessor_config.json
497 Bytes
| { | |
| "K": 257, | |
| "do_normalize": true, | |
| "feature_extractor_type": "MCTCFeatureExtractor", | |
| "feature_size": 80, | |
| "frame_signal_scale": 32768.0, | |
| "hop_length": 10, | |
| "mel_floor": 1.0, | |
| "n_fft": 512, | |
| "normalize_means": true, | |
| "normalize_vars": true, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "preemphasis_coeff": 0.97, | |
| "return_attention_mask": false, | |
| "sample_size": 400, | |
| "sample_stride": 160, | |
| "sampling_rate": 16000, | |
| "win_function": "hamming_window", | |
| "win_length": 25 | |
| } | |