IBM/video-summarizer-using-watson

In this code pattern you will learn about building a robust solution for analyzing the video or audio files to quickly generate meaningful summary & insights using different Deep learning and Machine learning approaches. You will also learn about improving the readibility of the transcripts with IBM Watson Speech to Text speech recognition models, how to optimize the parameteres, train different speech to text models and learn about different state of the art language models used for summarizing the text.

Jupyter NotebookApache-2.0