0

0 9up Ast Ft

Developed by mazkooleg
This model is a fine-tuned audio classification model based on MIT/ast-finetuned-speech-commands-v2 on the digital speech commands dataset, primarily used for recognizing 0-9 digit speech commands
Downloads 19
Release Time : 2/26/2023

Model Overview

This is a fine-tuned Audio Spectrogram Transformer (AST) model, specifically designed for speech command recognition tasks, excelling in digit recognition

Model Features

High accuracy
Achieves 99.79% accuracy on the evaluation set
Fine-tuning optimization
Optimized based on pre-trained models on specific speech command datasets
Efficient training
Utilizes techniques like gradient accumulation for efficient training

Model Capabilities

Digit speech recognition
Audio classification
Command word detection

Use Cases

Voice interaction
Digital voice input system
Used for voice interaction systems requiring numeric input
High-accuracy digit recognition
Voice-controlled devices
Supports digital command control for smart home or industrial equipment
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase