ast-finetuned-audioset-10-10-0.4593-finetuned-ie Open-source Audio Classification Model

Ast Finetuned Audioset 10 10 0.4593 Finetuned Ie

Developed by minoosh

This model is a fine-tuned audio classification model based on MIT/ast-finetuned-audioset-10-10-0.4593, achieving 60.76% accuracy on the evaluation set.

Audio Classification

Transformers

Open Source License:Bsd-3-clause #Audio Classification #Transfer Learning #High Accuracy

Downloads 14

Release Time : 4/26/2023

Model Overview

This is a fine-tuned model for audio classification, based on the AST (Audio Spectrogram Transformer) architecture, optimized for specific datasets.

Model Features

Efficient Audio Processing

Based on AST architecture, capable of efficiently processing audio spectrograms

Fine-tuning Optimization

Fine-tuned on specific datasets to improve classification performance

Model Capabilities

Audio Classification

Spectrogram Analysis

Use Cases

Audio Analysis

Environmental Sound Classification

Identify and classify different types of sounds in various environments

Evaluation accuracy 60.76%

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

Ast Finetuned Audioset 10 10 0.4593 Finetuned Ie

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 ast-finetuned-audioset-10-10-0.4593-finetuned-ie

🚀 Quick Start

📚 Documentation

Training hyperparameters

Framework versions

📄 License