Signed
5K+
1
ast-finetuned-audioset-10-10-0.4593
:Byjozu
Use the Pull Tag button to download this ModelKit.
Or, read our KitOps documentation to learn how to use kit unpack --filter to download only the components you need.
ModelKit Tag Metadata
- Author
- MIT
- Date added
- Size
- 692.8MB
- Digest
- Total pulls
- 3K+
Package
- Name
- ast-finetuned-audioset-10-10-0.4593
- Version
- 1.0.0
- Authors
- MIT
- Description
- Audio Spectrogram Transformer (AST) model fine-tuned on AudioSet. The Audio Spectrogram Transformer is equivalent to ViT, but applied on audio. Audio is first turned into an image (as a spectrogram), after which a Vision Transformer is applied. The model gets state-of-the-art results on several audio classification benchmarks.
Model
- Name
- model.safetensors
- Path
- model.safetensors
- License
- BSD-3 clause
- Parameters
N/A