AIbase
EN
Home
Trillsson3 Ft Keyword Spotting
T

Trillsson3 Ft Keyword Spotting

Developed by vumichien
An audio classification model based on the TRillsson3 architecture, fine-tuned on the superb dataset for keyword spotting tasks
Audio Classification
Transformers
#Voice Keyword Detection#High-Accuracy Audio Classification#Non-Semantic Speech Features
Downloads 30
Release Time : 11/28/2022

Model Overview

This model is a fine-tuned version of vumichien/nonsemantic-speech-trillsson3 on the superb dataset, primarily used for keyword spotting tasks, achieving 90.41% accuracy on the evaluation set.

Model Features

High Accuracy
Achieves 90.41% accuracy on the superb dataset
Fine-Tuned Model
Based on the TRillsson3 pre-trained model, adapted for keyword spotting tasks
Efficient Training
Uses Adam optimizer and mixed-precision training for high training efficiency

Model Capabilities

Audio Classification
Keyword Spotting
Speech Feature Extraction

Use Cases

Voice Interaction
Voice Assistant Wake Word Detection
Detects device wake words like 'Hey Siri' or 'OK Google'
90.41% accuracy
Voice Command Recognition
Recognizes short voice commands
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase