This is part of a Practical Course project in GU to analyze speech data from the German Parliament's 20 election periods. It includes website scraping using Jsoup, parsing from XMI and XML files, and saving in MongoDB.
For speech analysis, SpaCy, Gervader, and Parlbert DUUI drivers have been used to process the data. WhisperX was used to get the transcript, segments, and timestamps for video speech analysis.