Video Transcripts Summarization using OpenAI Whisper and GPT Model

Abstract

Abstract: In today’s digital age, a vast amount of video content is generated and shared on the internet every minute. However, extracting relevant information from these videos can be time-consuming and challenging. This is where video transcript summarization comes in, providing a concise summary of video content without the need to watch the entire video. The video transcript summarization system aims to streamline the process of extracting key insights and information from video content by generating concise and informative summaries from their transcripts. In the dynamic landscape of video content, existing approaches to transcript summarization have encountered challenges that limit their effectiveness. Issues such as compromised accuracy, prolonged processing times and a restricted focus on YouTube's captioned videos have prompted the exploration of alternative solutions. This paper introduces a novel approach that tackles these limitations head-on, employing innovative technologies to redefine the landscape of video transcript summarization. To address the identified limitations, we propose an alternative strategy that hinges on the utilization of advanced technologies like OpenAI Whisper Model Automatic Speech Recognition(ASR) for video’s Transcription and Generative Pre-trained Transformer (GPT) model for Summarization. Through the integration of the OpenAI Whisper model for transcription and GPT models for summarization, our proposed approach strives to redefine standards in accuracy, processing efficiency, multilingual support, and exhibit the capability to generate either extractive or abstractive summaries. In the context of natural language processing (NLP) and text summarization ROUGE (Recall-Oriented Understudy for Gisting Evaluation) metrics will be used to evaluate the quality of generated summaries compared to human referenced summaries