Extracting Relevant Information from Video Recordings - Investigate Phase
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" ...