Logo Lanfrica

tarek-hossam-telecom/EsharaTalk-AI

Domaine:

natural language processing

Type de record:

softwareproject
Créateur:
tar
Hôte:
An AI-powered real-time Egyptian Sign Language translator using MediaPipe and OpenCV, featuring Text-to-Speech (gTTS) integration. > [!IMPORTANT] > ### ⚠️ Status: Work in Progress (WIP) > This project is currently under active development. I'm working on adding more signs and improving the AI model accuracy. > # 🖐️ EsharaTalk EG - Egyptian Sign Language Translator An AI-powered application that translates Egyptian Sign Language into spoken Arabic in real-time. ## 🚀 Features - **Hand Tracking:** Uses MediaPipe for high-precision hand landmark detection. - **Real-time Translation:** Detects signs like (Yes, No, Thank you, Hello) instantly. - **Voice Feedback:** Converts translated text into Arabic speech using gTTS. - **Web Interface:** Built with Streamlit for a smooth user experience. ## 🛠️ Tech Stack - Python - OpenCV & MediaPipe (Computer Vision) - Streamlit (Web Framework) - gTTS (Google Text-to-Speech)