Feature Extraction
Transformers
PyTorch
Safetensors
hubert
speech processing
self-supervision
african languages
🇪🇺 Region: EU
Instructions to use Orange/SSA-HuBERT-base-5k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Orange/SSA-HuBERT-base-5k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Orange/SSA-HuBERT-base-5k")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("Orange/SSA-HuBERT-base-5k") model = AutoModel.from_pretrained("Orange/SSA-HuBERT-base-5k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from Orange/SSA-HuBERT-base-5k: direct link, hf CLI and curl.
- Browser
- Download file 184 Bytes
-
https://huggingface.co/Orange/SSA-HuBERT-base-5k/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://Orange/SSA-HuBERT-base-5k/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/Orange/SSA-HuBERT-base-5k/resolve/main/preprocessor_config.json
184 Bytes
| { | |
| "do_normalize": true, | |
| "model_type": "hubert", | |
| "feature_size": 1, | |
| "padding_side": "right", | |
| "padding_value": 0, | |
| "return_attention_mask": false, | |
| "sampling_rate": 16000 | |
| } | |