Speech recognition

A speech recognition model can recognize spoken words and phrases, and may be used for other kinds of sound detection besides a human voice.

Currently, all speech recognition models that are compatible with the Edge TPU are feed-forward CNN architectures, so they're effective for short phrases only.

Trained models link

These models are trained and compiled for the Edge TPU.

Notice: These are not production-quality models; they are for demonstration purposes only.
Model name Detections/Dataset Input size Model size Downloads

Keyword Spotter v0.8

140+ phrases

32x198 578 KB

Edge TPU model,
Labels file

Example code link

Keyphrase detector

A few examples using the Keyword Spotter model to detect over 140 short phrases such as "start game" and "next song." Includes a snake game and a YouTube player that respond to voice commands.

Languages: Python