Ast Finetuned Audioset 10 10 0.4593

🚀 Audio Spectrogram Transformer (fine-tuned on AudioSet)

An Audio Spectrogram Transformer (AST) model fine-tuned on AudioSet, achieving state-of-the-art results in audio classification.

🚀 Quick Start

The Audio Spectrogram Transformer (AST) is a model fine - tuned on AudioSet. It was introduced in the paper AST: Audio Spectrogram Transformer by Gong et al. and first released in this repository.

Disclaimer: The team releasing Audio Spectrogram Transformer did not write a model card for this model so this model card has been written by the Hugging Face team.

✨ Features

• Based on the concept of Vision Transformer (ViT), but applied to audio data.
• Turns audio into spectrogram images and then applies a Vision Transformer.
• Achieves state - of - the - art results on several audio classification benchmarks.

📚 Documentation

Model description

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.

Usage

You can use the raw model for classifying audio into one of the AudioSet classes. See the documentation for more info.

📄 License

This model is released under the BSD 3 - Clause license.