AI4Bharat - IndicBART: Multilingual Sequence-to-Sequence Model
A BART-based model pre-trained for various sequence-to-sequence tasks across multiple Indian languages.
AI4Bharat
Nikhil_Narasimhan
About Model
IndicBART is a multilingual sequence-to-sequence model pre-trained for various tasks across multiple Indian languages. Based on the BART architecture, it is designed to handle tasks such as translation, summarization, and text generation. IndicBART aims to provide a unified model capable of understanding and generating text in diverse Indian languages, thereby facilitating a wide range of NLP applications.
AI4Bharat - IndicBART: Multilingual Sequence-to-Sequence Model
Metadata
MIT
Divyanshu Kakwani and Anoop Kunchukuttan and Satish Golla and Gokul N.C. and Avik Bhattacharyya and Mitesh M. Khapra and Pratyush Kumar
Multilingual Sequence-to-Sequence Model
open
AI4Bharat
Sector Agnostic
21/02/25 13:21:15
Nikhil Narasimhan
0
Activity Overview
15 
98 
0
Tags
- Multilingual
- Indian Languages
- NLP
- Sequence-to-Sequence
- BART
License Control
MIT
Version Control
No Version(s) Found
© 2025 - Copyright AIKosha. All rights reserved. This portal is developed by National e-Governance Division for IndiaAI mission.