Intro to TensorFlow Lite Part 3: Speech Recognition on Raspberry Pi | DigiKey

In this tutorial series, Shawn covers the basics for training a neural network with TensorFlow Lite to respond to a spoken word. This neural network model is deployed to a Raspberry Pi, where it can listen for the wake word in real time.

In this episode, Shawn provides the steps necessary to convert a Keras model to a TensorFlow Lite model, which is then deployed to a Raspberry Pi. The Pi will run a custom Python program that performs inference on captured audio data from a USB microphone. Upon hearing the wake word, the Pi can be made to perform any number of actions, but we’ll start by just flashing an LED.