This project provides a web application for scanning images and videos with Amazon Rekognition to retrieve a list of labels for the media asset. These labels are then used to query a sound library and retrieve a bundle of audio clips that will form an audio backdrop for the media asset.
-
Configure AWS credentials: https://docs.aws.amazon.com/cli/latest/userguide/cli-configure-files.html
-
Create a Python virtual environment:
$ virtualenv .venv
-
Activate the virtual environment:
$ source .venv/bin/activate
-
Install Python dependencies:
$ pip install -r requirements.txt
-
Run the server locally:
$ npm run build $ npm start
-
Open http://127.0.0.1:8000/ in a web browser