Instructions to use microsoft/unispeech-sat-base-plus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/unispeech-sat-base-plus with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForPreTraining processor = AutoProcessor.from_pretrained("microsoft/unispeech-sat-base-plus") model = AutoModelForPreTraining.from_pretrained("microsoft/unispeech-sat-base-plus", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from microsoft/unispeech-sat-base-plus: direct link, hf CLI and curl.
- Browser
- Download file 213 Bytes
-
https://huggingface.co/microsoft/unispeech-sat-base-plus/resolve/9fdf0146ac52703b834f4cd3d6c12d8966cff281/preprocessor_config.json
- Command line
-
hf download hf://microsoft/unispeech-sat-base-plus@9fdf0146ac52703b834f4cd3d6c12d8966cff281/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/microsoft/unispeech-sat-base-plus/resolve/9fdf0146ac52703b834f4cd3d6c12d8966cff281/preprocessor_config.json
213 Bytes
| { | |
| "do_normalize": true, | |
| "feature_extractor_type": "Wav2Vec2FeatureExtractor", | |
| "feature_size": 1, | |
| "padding_side": "right", | |
| "padding_value": 0, | |
| "return_attention_mask": false, | |
| "sampling_rate": 16000 | |
| } | |