AI Challenge with GPT-3.5, Codex, DALL-E, and Whisper API

Hackathon Kick-Off Email

Hackathon Deadline

Unlocking Vision through AI Communication

Louis

Louis Jefferson Zhang

Around the world, there exists an inequality affecting visually impaired individuals who lack access to essential accessibility services. This has driven me to develop a software for Smart Glasses that blind people can wear.

SightCom2 software utilizes OpenAI technologies, namely Whisper for speech transcription, GPT-3.5 as a LLM, DALL-E for image generation; image captioning, OCR and color recognition models from Clarifai API. 

This software is served on streamlit cloud, and is a prototype that can potentially be deployed on a microprocessor, assembled in an integrated circuit, between input devices like camera and microphone, and output devices like speakers. 

Smart glasses software prototype for the visually impaired, utilizing OpenAI and Clarifai technologies

"Louis team on AI Challenge with GPT-3.5, Codex, DALL-E, and Whisper API Hackathon"

Team Idea

Submission