The purpose of this app is to use your camera to take photos of things around you and using a few helper API's we use image recognition to get some predictions of what it possibly could be as well as how sure we think the model came to it then we take that image, translate it to english, then use another API to translate the english text to another language of our choosing, then the app will speak to you.
I'm probably less than an hour away to getting this to work on web, I didnt have time to set up Amazon Polly
- Add TensorFlow and a few more ML API's
- Get this working on Web
- Add Amazon Polly or something similar
- CI/CD Set up
- Better Error Handling
- Add authentication
- Save preferences to some external store
- Save translations and cache the text
- Remove default image