Instructions to use facebook/encodec_32khz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/encodec_32khz with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="facebook/encodec_32khz")# pip install -U transformers accelerate # Load model directly from transformers import AutoFeatureExtractor, AutoModel extractor = AutoFeatureExtractor.from_pretrained("facebook/encodec_32khz") model = AutoModel.from_pretrained("facebook/encodec_32khz", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from facebook/encodec_32khz: direct link, hf CLI and curl.
- Browser
- Download file 234 Bytes
-
https://huggingface.co/facebook/encodec_32khz/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://facebook/encodec_32khz/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/facebook/encodec_32khz/resolve/main/preprocessor_config.json
234 Bytes
| { | |
| "chunk_length_s": null, | |
| "feature_extractor_type": "EncodecFeatureExtractor", | |
| "feature_size": 1, | |
| "overlap": null, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 32000 | |
| } | |