Multistaged machine learning pipeline that converts images of text (narration and dialogue) to a realistic audio rendering of said text. The audio rendering shall imitate human-like speech patterns.
Run the following commands:
virtualenv --python=/PATH/TO/PYTHON3.6+ venv
source ./venv/bin/activate
pip install -r requirements.txt
The virtualenv should always be active when developing or running code in this repo.
To deactivate the virtualenv, run deactivate.