D

Distilhubert Ft Keyword Spotting

Developed by anton-l
Keyword recognition model based on the DistilHuBERT architecture, fine-tuned on the superb dataset with an accuracy of 97.06%
Downloads 14
Release Time : 3/2/2022

Model Overview

This is an audio classification model for keyword recognition tasks, based on the lightweight DistilHuBERT architecture and fine-tuned on the superb dataset.

Model Features

High Accuracy
Achieves 97.06% accuracy on the evaluation set
Lightweight Architecture
Based on the DistilHuBERT architecture, more lightweight compared to the original HuBERT model
Efficient Training
Uses mixed-precision training to optimize training efficiency

Model Capabilities

Audio Classification
Keyword Recognition
Voice Command Detection

Use Cases

Smart Home
Voice-Controlled Devices
Recognizes specific wake words to control smart home devices
High accuracy in recognizing user commands
Voice Assistants
Wake Word Detection
Detects device wake words to activate voice assistants
Low false alarm rate and high recall rate
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase