Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{171601,
        author = {Aditi Bandaru and Anish Tirumani and Maneesha bhavana and Sowmya chitturi},
        title = {VIDEO TRANSCRIPTION},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {8},
        pages = {933-936},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=171601},
        abstract = {This project presents a web application for automated keyword extraction and analysis from video and audio content, including YouTube videos. Leveraging the Whisper speech recognition model and advanced natural language processing techniques, the application aims to provide efficient and accurate keyword extraction capabilities for various applications.
The system processes uploaded video files or YouTube URLs, extracting audio content and transcribing it using Whisper. Subsequently, TF-IDF or CountVectorizer algorithms are employed to identify significant keywords from the transcribed text. For YouTube videos, keyword accuracy is evaluated against available transcripts, while for uploaded files, user-provided expected keywords can be used for comparison. Performance metrics, including precision, recall, F1-score, and coverage score, are calculated to assess keyword extraction effectiveness.
The developed web application, built using the Flask framework, offers a user-friendly interface for seamless interaction and facilitates access to extracted keywords, full transcripts, and performance metrics. This tool holds potential applications in content analysis, information retrieval, video indexing, and automated metadata generation. The project demonstrates the feasibility of combining speech recognition and natural language processing for robust keyword extraction from multimedia content, offering valuable insights and efficiency improvements for content management and analysis workflows.},
        keywords = {},
        month = {January},
        }