Instructions to use bezzam/xcodec2-fe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bezzam/xcodec2-fe with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("bezzam/xcodec2-fe", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from bezzam/xcodec2-fe: direct link, hf CLI and curl.
- Browser
- Download file 293 Bytes
-
https://huggingface.co/bezzam/xcodec2-fe/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://bezzam/xcodec2-fe/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/bezzam/xcodec2-fe/resolve/main/preprocessor_config.json
293 Bytes
| { | |
| "feature_extractor_type": "Xcodec2FeatureExtractor", | |
| "feature_size": 80, | |
| "hop_length": 320, | |
| "n_channels": 1, | |
| "num_mel_bins": 80, | |
| "padding_side": "right", | |
| "padding_value": 1, | |
| "pre_padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000, | |
| "stride": 2 | |
| } | |