H

Hubert Base Superb Ks

Developed by superb
This model is a keyword spotting model based on the Hubert architecture, designed to classify speech segments into predefined keyword sets.
Downloads 11.29k
Release Time : 3/2/2022

Model Overview

This model is a ported version of S3PRL's Hubert model for the SUPERB keyword spotting task, based on the hubert-base-ls960 pre-trained model, suitable for 16kHz sampled speech audio.

Model Features

High Accuracy
Achieves 96.72% accuracy on the Speech Commands Dataset v1.0
Hubert-based Architecture
Uses hubert-base-ls960 as the base model, with powerful speech feature extraction capabilities
Lightweight Application
Suitable for on-device deployment, enabling fast response

Model Capabilities

Speech Classification
Keyword Spotting
Voice Command Detection

Use Cases

Smart Device Control
Voice Command Recognition
Recognize device control commands such as 'turn on the light', 'turn off the light', etc.
Accurately identifies predefined keyword commands
Voice Assistants
Wake Word Detection
Detect device wake words
Reduces false alarm rate and improves user experience
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase