Instructions to use hf-internal-testing/tiny-random-UnivNetModel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hf-internal-testing/tiny-random-UnivNetModel with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="hf-internal-testing/tiny-random-UnivNetModel")# pip install -U transformers accelerate # Load model directly from transformers import AutoFeatureExtractor, AutoModel extractor = AutoFeatureExtractor.from_pretrained("hf-internal-testing/tiny-random-UnivNetModel") model = AutoModel.from_pretrained("hf-internal-testing/tiny-random-UnivNetModel", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from hf-internal-testing/tiny-random-UnivNetModel: direct link, hf CLI and curl.
- Browser
- Download file 627 Bytes
-
https://huggingface.co/hf-internal-testing/tiny-random-UnivNetModel/resolve/aba2aff87a2bb15d7a1f31ec28303d56d60f9656/preprocessor_config.json
- Command line
-
hf download hf://hf-internal-testing/tiny-random-UnivNetModel@aba2aff87a2bb15d7a1f31ec28303d56d60f9656/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/hf-internal-testing/tiny-random-UnivNetModel/resolve/aba2aff87a2bb15d7a1f31ec28303d56d60f9656/preprocessor_config.json
627 Bytes
| { | |
| "center": false, | |
| "compression_clip_val": 1e-05, | |
| "compression_factor": 1.0, | |
| "do_normalize": false, | |
| "feature_extractor_type": "UnivNetFeatureExtractor", | |
| "feature_size": 1, | |
| "filter_length": 1024, | |
| "fmax": 12000.0, | |
| "fmin": 0.0, | |
| "hop_length": 256, | |
| "max_length_s": 10, | |
| "mel_floor": 1e-09, | |
| "model_in_channels": 64, | |
| "normalize_max": 2.3143386840820312, | |
| "normalize_min": -11.512925148010254, | |
| "num_mel_bins": 100, | |
| "pad_end_length": 10, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 24000, | |
| "win_function": "hann_window", | |
| "win_length": 1024 | |
| } | |