AccessLearnAI
An open-source pipeline tool for accessible learning that converts a single lecture audio input into four outputs: text transcription, a concise summary, speech audio, and braille. It uses a FastAPI, React, and Docker architecture.
Timeline (last 90 days)
Developer Vishal Mundewadi built AccessLearnAI, a tool that takes lecture audio as input and simultaneously outputs text transcription, a concise summary, speech audio and braille.
AccessLearnAI's pipeline consists of four stages: Whisper handles speech-to-text, T5 handles summary compression, edge-tts converts the summary back to speech, and finally the text is converted to braille.
AccessLearnAI's backend uses FastAPI with PostgreSQL for storage, the frontend is React plus TypeScript, deployment uses Docker containers running on GCP, and the frontend is hosted on Vercel.
AccessLearnAI's code is open-sourced on GitHub (vishal-mundewadi/AccessLearnAI), and an online demo is provided on Vercel.
All Facts (4)
Developer Vishal Mundewadi built AccessLearnAI, a tool that takes lecture audio as input and simultaneously outputs text transcription, a concise summary, speech audio and braille.
50%UnverifiedAccessLearnAI's pipeline consists of four stages: Whisper handles speech-to-text, T5 handles summary compression, edge-tts converts the summary back to speech, and finally the text is converted to braille.
50%UnverifiedAccessLearnAI's backend uses FastAPI with PostgreSQL for storage, the frontend is React plus TypeScript, deployment uses Docker containers running on GCP, and the frontend is hosted on Vercel.
50%UnverifiedAccessLearnAI's code is open-sourced on GitHub (vishal-mundewadi/AccessLearnAI), and an online demo is provided on Vercel.
50%