Santiago Rojas Tunjano
Published © GPL3+

AI-Powered Sign Language to Speech Translator

Translating Sign Language into English speech in real-time using an AI Model trained using a convoluted neural network.

IntermediateShowcase (no instructions)24 hours4,863
AI-Powered Sign Language to Speech Translator

Things used in this project

Hardware components

Raspberry Pi 3 Model B
Raspberry Pi 3 Model B
×1
Raspberry PI AI Camera
Raspberry PI AI Camera
×1

Software apps and online services

Raspbian
Raspberry Pi Raspbian
TensorFlow
TensorFlow
MobileNetV2

Hand tools and fabrication machines

3D Printer (generic)
3D Printer (generic)

Story

Read more

Custom parts and enclosures

Camera & Raspberry Pi Holder

The camera holder is expertly designed to securely position both the camera and Raspberry Pi, offering smooth adjustability. It features a rotating mechanism for easy orientation and a flexible neck that allows for precise angle adjustments, ensuring optimal camera positioning for any setup. This thoughtful design ensures both stability and versatility for various use cases.

Code

SpeakUp

This project is a real-time Sign Language Recognition System that uses a SONY AI camera and a Raspberry Pi to capture hand gestures and translate them into spoken English. To create it, first, collect sign language gesture images, preprocess them, and train a deep learning model using TensorFlow. After training, the model is quantized for efficient edge deployment, then transferred to the Raspberry Pi where it uses the camera to classify hand gestures in real-time. The system converts these gestures into text and uses eSpeak to transform the text into speech.

Credits

Santiago Rojas Tunjano
1 project • 16 followers
Contact

Comments

Please log in or sign up to comment.