AMB21/22/23 TensorFlow Lite - Micro Speech

This project demonstrated how to apply a simple machine learning model trained via Google TensorFlow, and transfer it to AMB21/22/23 board

Splendide_Mendax

Following Follow project

Liked Like project

Become a Hackaday.io member

Just one more thing

To make the experience fit your profile, pick a username and tell us what interests you.

OK, I'm done! Skip

Public Chat

Similar projects worth following

View Gallery

Public Chat

Description

This project demos how TFL Micro Speech Example works with Realtek AMB21/22/23 EVB.
A Micro Speech neural network is trained with TensorFlow Lite to respond to "yes" and "no".

Components

1 × AmebaD [ AMB23 / AMB21 / AMB22 ]
1 × Arducam Mini 2MP Plus OV2640 SPI Camera Module
1 × LED Fiber Optics / Emitters

Build Instructions

Collapse

1

AMB21 / AMB22 Wiring Diagram

Connect the microphone and LEDs to the AMB21/22 board following the diagram.
2

AMB23 Wiring Diagram:

As AMB23 has a built-in microphone on the board, there is no need for any external microphone. For the LEDs, we will only connect two LEDs and then use the two onboard LEDs (Blue and Green).
3
Firmware & Libraries Preparation
- Download the Ameba customized version of TensorFlow Lite for Microcontrollers library at https://github.com/ambiot/ambd_arduino/tree/master/Arduino_zip_libraries.
- Follow the instructions at https://www.arduino.cc/en/guide/libraries to install it.
- Ensure that the patch files found at https://github.com/ambiot/ambd_arduino/tree/master/Ameba_misc/ are also installed.