This is a simple system where we have allowed users to input PDF Textbooks and then generate videos from the text of those images. The following work has been done for the images:
- PDF to text conversion and text cleaning / pre-processing.
- Topic identification and extraction using NLP.
- Search images by topic and download from Bing API images.
- Create Audio for sentence using a Python text to speech library.
- Create MP4 video from images + text + audio using moviepy Library.
The Project has been written in Python 2.7 using Flask as a basic and simple server to run the code.
- Clone the project in a directory on your local system.
git clone https://github.com/salman-bhai/text2video
cd text2video/
- Create a new Virtual Environment using the Python Package
virtualenvand activate the virtual environment in it.
virtualenv venv
source venv/bin/activate
- Install the Python Dependencies in the same Python Virtual Environment by running the following command:
pip install -r requirements.txt
- You can start the server by running the following command:
python server.py
You will need to install certain NLTK Dependencies as well to get the code to run. Kindly look open an issue in case you miss anything.
- All Project Documentation is on the Wiki and in case anything is missing kindly feel free to open up a new Issue on the Github Issue Tracker for the same.