distilhubert-finetuned-gtzan Open-source Audio Classification Model - Finetuned on the GTZAN dataset, with an accuracy rate of 83%

Distilhubert Finetuned Gtzan

Developed by pranjalks

This model is an audio classification model fine-tuned on the GTZAN music classification dataset based on distilhubert, achieving an accuracy of 83%.

Audio Classification

Transformers

Open Source License:Apache-2.0 #Music Classification #High Accuracy Audio Model #Lightweight HuBERT

Downloads 18

Release Time : 8/20/2023

Model Overview

A lightweight audio processing model specifically designed for music genre classification, fine-tuned on the GTZAN dataset based on the DistilHuBERT architecture.

Model Features

Efficient and Lightweight

Lightweight architecture based on DistilHuBERT, reducing computational resource requirements while maintaining performance

High Accuracy

Achieves 83% accuracy on the GTZAN music classification dataset

Fast Training

Requires only 15 training epochs to achieve good performance

Model Capabilities

Music Genre Classification

Audio Feature Extraction

Music Content Analysis

Use Cases

Music Services

Automatic Music Classification

Automatically tag uploaded music genres for music streaming platforms

Automatic classification capability with 83% accuracy

Music Recommendation System

Personalized recommendations based on music genre analysis

Education & Research

Music Analysis Teaching

Used for teaching demonstrations in Music Information Retrieval (MIR) related courses

Property	Details
License	Apache - 2.0
Base Model	ntu - spml/distilhubert
Tags	generated_from_trainer
Datasets	marsyas/gtzan
Metrics	accuracy

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.1376	1.0	113	1.9783	0.44
1.3879	2.0	226	1.2784	0.66
1.0967	3.0	339	1.0352	0.66
0.8639	4.0	452	0.8977	0.7
0.6308	5.0	565	0.7466	0.76
0.4585	6.0	678	0.7374	0.78
0.5213	7.0	791	0.6039	0.79
0.1958	8.0	904	0.7174	0.8
0.2075	9.0	1017	0.5657	0.85
0.1034	10.0	1130	0.6176	0.8
0.0308	11.0	1243	0.7378	0.85
0.103	12.0	1356	0.7759	0.82
0.0131	13.0	1469	0.8104	0.83
0.0103	14.0	1582	0.8175	0.83
0.0116	15.0	1695	0.8444	0.83

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Distilhubert Finetuned Gtzan

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 distilhubert-finetuned-gtzan

🚀 Quick Start

📚 Documentation

Model Information

Model Index

Training and Evaluation

Training hyperparameters

Training results

Framework versions

📄 License