AI4Bharat - IndicBART: Multilingual Sequence-to-Sequence Model
A BART-based model pre-trained for various sequence-to-sequence tasks across multiple Indian languages.
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
N.A.
Open
Sector Agnostic
21/02/25 13:21:15
0
Activity Overview
0
31 
0 
305
Tags
- Multilingual
- Indian Languages
- NLP
- Sequence-to-Sequence
- BART
License Control
MIT
More Models from AI4Bharat
- 0
- 0
- 0
51
- 0
- 0
- 0
- 53
- 0
- 0
- 0
- 42
© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.