AI-Powered Sign Language Translation

Built an end-to-end web application that translates sign language gestures into text using computer vision and deep learning. The system uses MediaPipe to extract hand and pose landmarks, a PyTorch-based model to recognize signs, and a FastAPI backend with WebSockets for real-time communication. An LLM-based gloss-to-text pipeline then converts recognized signs into more natural continuous text, creating a complete sign-to-text workflow from visual input to language generation.