DistilHubert-Finetuned GTZAN Open-Source Audio Classification Model

Distilhubert Finetuned Gtzan

Developed by calvpang

This model is an audio classification model based on the DistilHuBERT architecture, fine-tuned on the GTZAN music classification dataset, primarily used for music genre classification tasks.

Audio Classification

Transformers

Open Source License:Apache-2.0 #Music Classification #High Accuracy #Audio Feature Extraction

Downloads 15

Release Time : 8/9/2023

Model Overview

This is a fine-tuned audio classification model specifically designed for identifying and classifying music genres. Based on the DistilHuBERT architecture and trained on the GTZAN dataset, it achieves an accuracy of 83%.

Model Features

Efficient Audio Feature Extraction

Based on the DistilHuBERT architecture, it can efficiently extract audio features.

High Accuracy

Achieves 83% accuracy on the GTZAN test set.

Lightweight

As a Distil version, it is more lightweight compared to the original HuBERT model.

Model Capabilities

Music Genre Classification

Audio Feature Extraction

Music Content Analysis

Use Cases

Music Services

Automatic Music Classification

Automatically classify uploaded music files for music streaming platforms.

Accuracy reaches 83%.

Music Recommendation System

Improve recommendation algorithms based on music genre classification results.

Music Research

Music Style Analysis

Used for style classification and analysis in musicology research.

Property	Details
Base Model	ntu - spml/distilhubert
Tags	generated_from_trainer
Datasets	marsyas/gtzan
Metrics	accuracy
Model Name	distilhubert - finetuned - gtzan
Task	Audio Classification
Dataset Name	GTZAN
Dataset Type	marsyas/gtzan
Dataset Config	all
Dataset Split	train
Dataset Args	all
Accuracy	0.83

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.1006	1.0	57	1.9678	0.39
1.5415	2.0	114	1.3971	0.7
1.1393	3.0	171	1.1602	0.7
1.0024	4.0	228	0.9230	0.77
1.0193	5.0	285	0.7550	0.82
0.5975	6.0	342	0.7155	0.83
0.608	7.0	399	0.6451	0.83
0.3833	8.0	456	0.6135	0.83
0.467	9.0	513	0.5864	0.84
0.3761	10.0	570	0.5930	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

Training Procedure

Training hyperparameters

Training results

Framework versions

📄 License