AIbase
EN
Home
Ast Finetuned Audioset 10 10 0.4593 Finetuned Gtzan
A

Ast Finetuned Audioset 10 10 0.4593 Finetuned Gtzan

Developed by vineetsharma
An audio classification model based on AST architecture, fine-tuned on the GTZAN dataset for music genre classification tasks
Audio Classification
Transformers
Open Source License:Bsd-3-clause#Audio Classification#High Accuracy#Music Genre Recognition
Downloads 14
Release Time : 7/2/2023

Model Overview

This model is an audio classification model based on the Audio Spectrogram Transformer (AST) architecture, pre-trained on the AudioSet dataset and fine-tuned on the GTZAN music dataset, specifically designed for music genre classification tasks.

Model Features

High Accuracy
Achieves 91% accuracy on the GTZAN test set
Transformer-based Architecture
Uses Audio Spectrogram Transformer to process audio spectral features
Two-stage Training
Pre-trained on the large-scale AudioSet dataset, then fine-tuned on the GTZAN music dataset

Model Capabilities

Music Genre Classification
Audio Feature Extraction
Spectral Analysis

Use Cases

Music Analysis
Automatic Music Genre Classification
Classify music clips by genre
91% accuracy
Music Recommendation System
Serve as a feature extraction component for music recommendation systems
Audio Processing
Audio Content Analysis
Analyze audio content features
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase