IndicBARTSS is a multilingual, sequence-to-sequence pre-trained model based on the mBART architecture, designed for Indic language generation tasks such as machine translation, summarization, and question generation. Supporting 11 Indic languages and English, it is smaller and more efficient than mBART50 and mT5. Trained on 452 million sentences, it eliminates the need for script mapping by using native scripts, making it ideal for low-resource language processing and fine-tuning.
MIT
Sector Agnostic
Raj Dabre and Himani Shrotriya and Anoop Kunchukuttan and Ratish Puduppully and Mitesh M. Khapra and Pratyush Kumar
N.A.
N.A.
N.A.
N.A.
N.A.
N.A.
N.A.
N.A.
Open
21/02/25 13:21:57
N.A.
0
© 2026 - Copyright AIKosh. All rights reserved.