Magor video transcript editor

Abstract

Due to the fast technological advancements, people are viewing and accessing more media content than ever before. Millions of people use the internet every day, and billions of fresh movies and audio are published on social media and video platforms by individuals all over the world. The outbreak of coronavirus in 2019 has led to a significant increase in the demand for video material. Millions of students have switched from traditional schooling to video and web-based learning. In order to cater to the large audience, many uploaders and platforms have included subtitles or closed captions for viewers to comprehend the video contents. Some of the video contents are manually transcribed, which is an expensive and time-consuming operation due to the need for numerous replays and relistens of the video. The emergency of Automatic Speech Recognition, on the other hand, has alleviated this problem. Transcripts may now be transcribed into a variety of languages to satisfy the needs of audiences all around the world. However, because these automatic captions are generated by a machine learning system, their accuracy will vary depending on video quality. As a result, there is still a need to re-evaluate the quality of captions. Therefore, we will analyse the different technologies as well as the benefits and drawbacks of existing transcribing tools before integrating the strategies to build the Magor Video Transcript Editor.