Instructions to use yangwang825/svector-aam-aug with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yangwang825/svector-aam-aug with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="yangwang825/svector-aam-aug", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("yangwang825/svector-aam-aug", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "SvectorModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_svector.SvectorConfig", | |
| "AutoModel": "modeling_svector.SvectorModel", | |
| "AutoModelForAudioClassification": "modeling_svector.SvectorModelForSequenceClassification" | |
| }, | |
| "hidden_size": 512, | |
| "hop_length": 10, | |
| "initializer_range": 0.02, | |
| "loss_fn": "aam", | |
| "mean_norm": true, | |
| "model_type": "svector", | |
| "n_mels": 80, | |
| "norm_type": "sentence", | |
| "num_classes": 5994, | |
| "num_heads": 8, | |
| "num_layers": 5, | |
| "sample_rate": 16000, | |
| "std_norm": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.31.0", | |
| "win_length": 25 | |
| } | |