RAG-Based AI Teaching Assistant: Audio Transcription & Labeling
I built a Retrieval-Augmented Generation (RAG) pipeline to transcribe and process educational videos using OpenAI's Whisper. I generated and stored document embeddings to retrieve contextual video chunks efficiently. I integrated Large Language Models to answer questions based on the processed video content. • Transcribed educational videos to text using audio processing tools. • Aligned processed transcript with video chunks for context retrieval. • Labeled data was used to support question answering accuracy. • Focus was on audio transcription and data preparation for AI teaching assistant.