Text-Transcriber

Introduction

The project can get the text from an image, then use Google's Text-to-Speech API to convert it into an audio file.

Website

We develop a website to deploy our model. You can easily use our service through that website.

If you want to use our website, please follow the steps bellow.

1. Git clone this repository.
2. Go to 'website' folder.
   cd website
3. Run main.py file.
   python main.py
4. Copy the server address, and open it in browser.

Resources

• For model training: https://github.com/githubharald/SimpleHTR
• For word detector: https://github.com/githubharald/WordDetector
• Google Text-to-Speech API