Objective : Making videos searchable based on their content.
The library 'moviepy' has been used to extract audio file in .WAV format from video .MP4 file.
The library 'SpeechRecognition' has been used to transcribe the extracted audio .WAV file into TEXT using the Google Web Speech API (FREE).
Two different keywords extraction NLP models has been explored to extract important keywords from the text transcript to tag the videos.
To interact with the programs, click "Open in Colab" after opening a specific notebook in this GitHub repository.