Copyright © 2025 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{163182,
        author = {Tanishque Sharma and Sujoy Mondol and Sandeep Kumar},
        title = {Enhanced Speech Recognition & Abstractive Text Summarisation with wav2vec2 & Pegasus},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {10},
        number = {11},
        pages = {982-991},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=163182},
        abstract = {In this study, Python machine learning techniques are used to present a comprehensive method for integrating text summarization with speech recognition. It leverages the cuttingedge Wav2Vec2 algorithm for accurate voice recognition, as well as the pre-trained Pegasus model for concise and informative text summaries. This research aims to develop an integrated model that can efficiently translate spoken language into written text and provide brief, logical summaries. This combination of technologies makes data analysis and understanding more efficient by addressing the increasing need to analyze and extract knowledge from large volumes of spoken content. As a result of the combination of these two potent machine learning methods, transcriptions are guaranteed to be accurate, as well as knowledge extraction is accelerated. Utilizing Wav2Vec2's spoken language handling capabilities and Pegasus's text summarization expertise, the proposed method bridges the gap between oral and written communication. A variety of applications are possible, such as transcribing speeches and interviews and condensing lengthy audio files.

},
        keywords = {Speech recognition, text summarization, machine learning, Wav2Vec2, Pegasus model, Python programming, data processing, knowledge extraction, audio-totext conversion, information retrieval, natural language processing.},
        month = {},
        }