DefinePK

Abstract

The process of deriving a summary from a given sequence of sentences is known as text summarization. There are two different kinds of summaries: extractive and abstractive. In an extractive summary, words are taken out of the original text and combined into a brief. In addition to reproducing the words from the input, the abstractive summary also creates new terms based on its comprehension of the text. This report explores the development and implementation of a system aimed at generating textual summaries of videos solely from audio content. The system utilizes cutting-edge approaches in Natural Language Processing (NLP) and Machine learning (ML), Language Models (LM). It employs Whisper model and BART model to transcribe spoken audio, extract meaningful information, and summarize the content to create concise video summaries. By combining these models and techniques, this system is capable to handle both English, Hindi/Urdu and the bilingual conversational videos and is generating the correct results with an average accuracy of 70% (ROGUE Score) and 100% of F1-Score (ROGUE).