Whisper Tiny Finetuned Gtzan
An audio classification model fine-tuned on the GTZAN dataset based on openai/whisper-tiny, achieving 91% accuracy
Downloads 17
Release Time : 7/2/2023
Model Overview
This model is a fine-tuned version of the Whisper-tiny architecture, specifically designed for music genre classification tasks, demonstrating excellent performance on the GTZAN dataset.
Model Features
High Accuracy
Achieves 91% classification accuracy on the GTZAN test set
Lightweight
Based on the whisper-tiny architecture with a smaller parameter size, suitable for resource-limited environments
Fast Convergence
Requires only 10 training epochs to reach optimal performance
Model Capabilities
Music Genre Classification
Audio Feature Extraction
Use Cases
Music Analysis
Automatic Music Classification
Automatically classifies music clips by genre
Accurately identifies 10 music genres
Music Recommendation System
Serves as a pre-classification module for music recommendation systems
Featured Recommended AI Models
Š 2025AIbase