AI-Powered Transcript Summarization and Question Answering for YouTube and Wikipedia

With the rapid growth of online content, there is an increasing demand for efficient tools that facilitate content understanding and knowledge retention. This research focuses on the development of an AI-powered system designed to automate summarization, question answering, and quiz generation from YouTube transcripts and Wikipedia articles. The system employs advanced natural language processing (NLP) techniques to process and distill complex information into clear and concise summaries. The process begins with the extraction of text through the YouTube Transcript API or web scraping. The Pegasus-XSum model is then used for summarizing the content, ensuring that key information is retained while minimizing text length. For question answering, the Llama model is employed to generate contextually relevant answers based on the provided content. Additionally, the system generates quizzes by extracting entities from the text to enhance interactive learning. This technology aims to improve content comprehension, making it especially valuable for educational settings and knowledge management. By integrating summarization, question answering, and quiz generation into a single platform, the system supports efficient learning and better retention of critical information. This research demonstrates the potential of NLP in addressing the challenges of information overload and facilitating effective knowledge acquisition.