README.md

metadata

title: Music Classification with MIT AST
emoji: 🎵
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.9.1
app_file: app.py
pinned: false
license: mit

Audio Classification App

This is an audio classification application that uses the MIT AST (Audio Spectrogram Transformer) model to classify audio files. The model can recognize various sounds and music categories from the AudioSet dataset.

Features

• Simple web interface for audio file upload
• Real-time classification using Hugging Face's AST model
• Displays classification results in JSON format

Usage

1. Open the web interface
2. Upload an audio file (supports various formats including MP3, WAV, etc.)
3. Wait for the classification results
4. View the predicted categories and their confidence scores

Technical Details

• Built with Gradio for the web interface
• Uses Hugging Face's AST model (MIT/ast-finetuned-audioset-10-10-0.4593)
• Deployed on Hugging Face Spaces

Requirements

The required packages are listed in requirements.txt