- To accomplish video summarization, one must possess fundamental comprehension and assessment skills regarding the content. In this project, an AI-based video summarization system using FFmpeg, Natural Language Processing (NLP) techniques, and AssemblyAI has been developed. The system aids in generating an accurate summary. We analyse previous works and suggest a fair data split for future reference. The parallel attention mechanism that utilizes static and motion features significantly improves the results for the SumMe dataset and performs well for other datasets as well. The primary aim is to provide users with an efficient way to comprehend video content, and the system's effectiveness is evaluated based on the accuracy and comprehensiveness of the generated summaries and user satisfaction with the system's functionality.

Keywords : AI-based, Video Summarization, FFmpeg, NLP, AssemblyAI, Static Features, Motion Features, SumMe Dataset, Accuracy, Comprehensiveness, user Satisfaction, Data Split, Benchmarking.