Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/derailed-dash/image-text-translator
Image Text Extractor and Translator Application: Containerised Python Flask UI, and Google Cloud Functions backend, which calls Google Cloud prebuilt ML APIs
https://github.com/derailed-dash/image-text-translator
cloud-functions cloud-run flask google-cloud google-cloud-translation-api google-cloud-vision-api jinja2-templates python
Last synced: 8 days ago
JSON representation
Image Text Extractor and Translator Application: Containerised Python Flask UI, and Google Cloud Functions backend, which calls Google Cloud prebuilt ML APIs
- Host: GitHub
- URL: https://github.com/derailed-dash/image-text-translator
- Owner: derailed-dash
- Created: 2024-06-09T23:07:14.000Z (8 months ago)
- Default Branch: master
- Last Pushed: 2024-10-04T14:52:58.000Z (4 months ago)
- Last Synced: 2024-12-03T09:09:48.645Z (2 months ago)
- Topics: cloud-functions, cloud-run, flask, google-cloud, google-cloud-translation-api, google-cloud-vision-api, jinja2-templates, python
- Language: Python
- Homepage: https://image-text-translator.just2good.co.uk/
- Size: 2.35 MB
- Stars: 1
- Watchers: 2
- Forks: 1
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Image Text Extract and Translation
## Overview
An application that allows a user to upload an image containing text. The text will be extracted, and translated to any selected language.
E.g. A user wants to translate a meme in Ukrainian, to English.
It is built using:
- Python Flask for the UI
- Event driven functions for the backend
- Google Cloud serverless components for hosting: i.e. Cloud Run and Cloud Functions
- Google pre-built ML APIs for the extraction and translation
## Repo Structure
```text
└── image-text-translator
├── docs/
|
├── infra-tf/ - Terraform for installing infra
|
├── scripts/ - For environment setup and helper scripts
| ├── 00_image-text-translator-sa-setup.sh - Initial sa setup
| ├── 01_env_setup.sh - Env setup - run with each new session
| └── 02_deployment_sa.sh - Deployment sa setup
|
├── app/ - The Application
│ ├── ui_cr/ - Browser UI (Cloud Run)
│ │ ├── static/ - Static content for frontend
| | ├── templates/ - HTML templates for frontend
| | ├── app.py - The Flask application
| | ├── requirements.txt - The UI Python requirements
| | ├── Dockerfile - Dockerfile to build the Flask container
| | └── .dockerignore - Files to ignore in Dockerfile
| |
│ └── backend_gcf/ - Backend (Cloud Function)
│ ├── main.py - The backend CF application
│ └── requirements.txt - The backend CF Python requirements
|
├── testing/
│ └── images/
|
├── requirements.txt - Python requirements for project local dev
└── README.md - Repo README
```
## Walkthrough and Detailed Guide
Check out my [Medium blog](https://medium.com/google-cloud/building-a-serverless-image-text-extractor-and-translator-using-google-cloud-pre-trained-ai-adfdccdb18d9), where I describe:
- How the solution is architected
- Design choices and rationale
- A walkthrough of how you can do the same, end-to-end, including:
- Dev environment setup (including Google Cloud SDK, VS Code, Cloud Code)
- Service accounts and roles
- Application Default Credentials (ADC)
- The coding for the UI (Python, Flask, Jinja templates) and backend (Python)
- How to test locally
- How to deploy to Google Cloud (using Google Artifact Registry and Cloud Build)
- Cost management tips
- Performance tips
## Todo
Some improvements I'll make soon...
- Captcha
- CI/CD
- IaC