TensorFlow 2.0 Beta is available Learn more

Transfer learning audio recognizer

In this tutorial, you will learn how to build a custom audio classifier that you will train in the browser using TensorFlow.js. You will use it to control a slider in the browser by making sounds.

You will use transfer learning to make a model that classifies short sounds with relatively little training data. You will be using a pre-trained model for speech command recognition. You will train a new model on top of this model to recognize your own custom sound classes.

This tutorial is presented as a codelab. Follow this link to open the codelab