EchoSign is a web tool that translates ASL into both text and spoken English, designed for use with video chat platforms like Zoom. It does more than just translate signs—EchoSign also adds grammar and sentence structure to produce spoken-like English, allowing individuals who are mute and deaf to engage in conversations seamlessly.

Features

Requirements

Setup

Usage

Real-time ASL translation to text and speech.

Easy-to-use GUI.

Python 3x

OpenCV

Mediapipe

TensorFlow

streamlit

Install python version >=3.10

Install packages cv2, mediapipe and TensorFlow

Download all the .py files

Run using “streamlit run app.py” on command line

On the web application, click the start camera button and start communicating using ASL. When you are done recording, click the stop camera button. Now click interpret to allow the backend to process the video and give the output. You can also click the speak button for a voice output.