As part of Mission Bhashini, we are developing a comprehensive Machine Translation system for English-to-Indian languages and vice versa. This project focuses on creating high-quality parallel corpora and robust bi-directional Neural Machine Translation (NMT) models to deliver robust and efficient translations.
The goal is to develop and deploy a Machine Translation system as a service for English to Hindi, Marathi, Gujarati, Odia, Kannada, and Malayalam languages and vice versa. The project covers:
- Creation of linguistic resources
- Development of a Machine Translation system as a service
Target Domains:
- Governance and Policy (Primary)
- Science and Technology
- Education
- Health
- Agriculture
The project is being carried out in collaboration with the following institutions:
- Centre for Development of Advanced Computing (C-DAC), Pune
- Centre for Development of Advanced Computing (C-DAC), Noida
- Indian Institute of Technology (IIT) Bombay
- IIIT Hyderabad
- AU-KBC, Anna University Chennai
- Banasthali Vidyapith
- C-DAC Bengaluru
- C-DAC Trivandrum
- Dharmsinh Desai University, Gujarat
- IIIT Bhubaneswar, Odisha
Parallel corpora generated under the EILMT Project, encompassing English to Hindi, Marathi, Gujarati, Odia, Kannada, and Malayalam languages. These datasets provide a robust foundation for developing and fine-tuning Machine Translation (MT) models.
Ready-to-use models designed for diverse translation tasks. These models can be utilized directly or fine-tuned for specific applications to achieve improved performance.
Download the EIMT models from the following link: Download Models
You can directly check the NMT models using the web interface:
EILMT Web Interface
Ensure that all necessary requirements and dependencies are installed to run the models efficiently. For more details, refer to the provided document along with Models.
The resources in this repository are released under the Creative Commons Attribution 4.0 International License (CC-BY 4.0). This license permits sharing and adaptation of the material, provided appropriate credit is given.
For inquiries, please contact us at:
eilmt.nltm@gmail.com