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 Micro 1 Model size Downloads

Keyword Spotter v0.8

140+ phrases

198x32x1 No 578 KB

Edge TPU model,
Labels file

1 Indicates compatibility with the Dev Board Micro. Some models are not compatible because they require a CPU-bound op that is not supported by TensorFlow Lite for Microcontrollers or they require more memory than available on the board. (All models are compatible with all other Coral boards.)

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