Audio summarization in real time for podcast, speeches and audio books

Abstract

As a result of the coronavirus disease (COVID-19) epidemic, most government work is now completed online. First- level medical checkups are regularly held online, online learning is now a widely available service at establishments around the globe, and organisations now hold all of their monthly meetings online. There is an abundance of widely accessible online meeting software on the market, including Google Meet, Microsoft Team, and others. This essay will examine a subject with numerous practical applications. In this paper, we present a method for creating a written or audio summary of a recorded video from its input. The described approach can also be used to create meeting minutes, create subtitles, or extract lecture notes for fun from lecture recordings. The system gives users the option of using the text summary or creating an audio output that matches the text summary. The suggested approach is put into practise with Python, and the suggested strategy is evaluated with the help of quick YouTube videos. Because  there is no existing dataset for the relevant study and no benchmark measure for efficiency evaluation, the proposed method is manually evaluated on the downloaded video collection.