Support for AST Model

[TheRealSal]

🌟 New adapter setup

Model description

The Audio Spectrogram Transformer model was proposed in AST: Audio Spectrogram Transformer by Yuan Gong, Yu-An Chung, James Glass. The Audio Spectrogram Transformer applies a Vision Transformer to audio, by turning audio into an image (spectrogram).

Open source status

• the model implementation is available: available in the HF Transformers library. Original Implementation: https://github.com/YuanGongND/ast
• the model weights are available: "MIT/ast-finetuned-audioset-10-10-0.4593"
• who are the authors: Yuan Gong @YuanGongND , Yu-An Chung and James Glass