Spektra- Video Insights Extraction

 Guiding Questions: Who is the target audience for this application? Are there any limitations or restrictions in terms of video format, length or language? What specific insights can the application extract from videos? Where can we find videos that will allow us to train our model? What technologies are used to transcribe audio from videos into text? From where do we acquire data? For this project, we decided to start off with Google Meet recordings for the various online courses held at Esprit, the majority being in French language. That is why we decided to partner up with Esprit as they will be providing us with the required resources and data in order to train this model and make this project come to life. We will also be gathering various educational and business videos as data from different platforms, mainly Coursera and YouTube.   Model pipeline: Converting videos to audio data using MoviePy library Speech Recognition and transcription using the "SpeechRecognition"

Introduction: As technology continues to advance, video content   has become an increasingly popular form of communication  and expression. From tutorials and presentations to  entertainment, advertisements and meetings, video is a  versatile medium that can convey a wealth of information and  emotions. However, extracting insights from video can be  challenging, especially if you have many videos to analyze and  you are a person who can’t focus during online sessions.  Fortunately, there is now a solution that can help you unlock  the full potential of your video content: an application that  automatically extracts insights from video. The application leverages NLP to analyze the audio and visual  elements of a video and identify patterns, trends, and key  insights. Whether you want to understand the sentiment of  your audience, track the performance of your marketing  campaigns, or analyze customer feedback, the application  provides you with a comprehensive and actionable overview o