YamNet

简介

Audio Event classification Model.
An audio event classifier trained on the AudioSet dataset to predict audio events from the AudioSet ontology employing the Mobilenet_v1 depthwise‑separable convolution architecture.

效果视频

规格与下载

技术细节

Model checkpoint:yamnet.pth
Input resolution:1x1x96x64
Number of parameters:3.73M
Model size (float):14.2 MB

应用领域

Audio Recognition

授权信息

Source Model: MIT
Deployable Model: AI-HUB-MODELS-LICENSE