Instructions to use WaveGenAI/audiomae with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WaveGenAI/audiomae with Transformers:
# Load model directly from transformers import PretrainedAudioMAEEncoder model = PretrainedAudioMAEEncoder.from_pretrained("WaveGenAI/audiomae", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "PretrainedAudioMAEEncoder" | |
| ], | |
| "img_size": [ | |
| 1024, | |
| 128 | |
| ], | |
| "in_chans": 1, | |
| "model_type": "audiomae", | |
| "num_classes": 0, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.45.2" | |
| } | |