![Logo](https://raw.githubusercontent.com/indian-nlp/nanoGPT-assamese/main/ss/ico.jpg)
NanoGPT trained on Assamese dataset
Releasing Soon to Public
Explore the docs »
Report Bug
·
Request Feature
Table of Contents
(#about-the-project)
Assamese or Asamiya is an Indo-Aryan language spoken mainly in the north-eastern Indian state of Assam, where it is an official language. It serves as a lingua franca of the wider region and has over 15 million native speakers according to Ethnologue.
This project aims to train the nanoGPT using an Assamese language dataset.
Contributions are welcome! Please see the Contributing section to get started.
- nanoGPT
- dataset: arambhani.txt
To run this code locally, follow these steps.
- Web Browser
- Clone the repo
git clone https://github.com/indian-nlp/nanoGPT-assamese.git
- Go to the project repo folder
cd path\to\directory
- Create Virtual Env (Recommended)
virtualenv venv_name
- Install the required Python packages using pip
pip install -r 'requirements.txt'
- Run the sample.py file to get the sample of the model
or, provide a starting text to generate from:
python sample-old.py --out_dir=out-assamese --device=cpu
python sample-old.py --out_dir=out-assamese --device=cpu --start=কৃতাঞ্জলি
See the open issues for a list of proposed features and known issues.
Contributions are welcome! Any contributions you make are greatly appreciated.
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature
) - Commit your Changes (
git commit -m 'Add some AmazingFeature'
) - Push to the Branch (
git push origin feature/AmazingFeature
) - Open a Pull Request
Don't forget to give the project a star! Thank you!
MIT License.
Sagar Tamang - LinkedIn - cs22bcagn033@kazirangauniversity.in
Official Website: https://sagartamang.com
Project Link: https://github.com/indian-nlp/nanoGPT-assamese
- I would like to thank ChatGPT for helping me debug all the errors.