This web application uses the transformers library from Hugging Face to perform language detection and translation of text files using the T5 model. The script also utilizes Flask framework for building the web interface.
These instructions will help you set up this project on your local machine for development and testing purposes.
Ensure Python (version >= 3.6) is installed in your system. You may download it from https://www.python.org/downloads/. Also, make sure you have installed required libraries by running the command below:
Download your model from hugginface
pip install -r requirements.txt
however it was not necessary for the madlad model but
we use language detection based on implementation available at https://github.com/Mimino666/langdetect. Installation guide is provided within their repository.
Run the main application by executing the following command:
python m2m100_translate.py
Open a browser window and navigate to URL shown in console (usually http://127.0.0.1:5000/). If needed, append appropriate language codes to access specific features.
- Flask - A lightweight WSGI web application framework.
- Transformers - State-of-the-art Machine Learning for Natural Language Processing.
- Mehdi Hosseini - Github
This project is licensed under the MIT License - see the LICENSE.md file for details