Indic Trans2

AI4Bharat's Indic-Trans-v2 is a multilingual Transformer (~1.1BM) NMT model trained on Samanantar v2 dataset which is the largest publicly available parallel corpora collection for languages of India at the time of writing (23 March 2023). We currently release two models - Indic to English and English to Indic and support all the 22 scheduled languages of India.

Digital India BHASHINI Division
BHASHINI_shailendra

About Model

Bhashini - IndicTrans2 is the first open-source transformer-based multilingual NMT model that supports high-quality translations across all the 22 scheduled Indic languages — including multiple scripts for low-resouce languages like Kashmiri, Manipuri and Sindhi. It adopts script unification wherever feasible to leverage transfer learning by lexical sharing between languages. Overall, the model supports five scripts Perso-Arabic (Kashmiri, Sindhi, Urdu), Ol Chiki (Santali), Meitei (Manipuri), Latin (English), and Devanagari (used for all the remaining languages).

We open-souce all our training dataset (BPCC), back-translation data (BPCC-BT), final IndicTrans2 models, evaluation benchmarks (IN22, which includes IN22-Gen and IN22-Conv) and training and inference scripts for easier use and adoption within the research community. We hope that this will foster even more research in low-resource Indic languages, leading to further improvements in the quality of low-resource translation through contributions from the research community.

This code repository contains instructions for downloading the artifacts associated with IndicTrans2, as well as the code for training/fine-tuning the multilingual NMT models.

For more details about the use of model, refer to github: https://github.com/AI4Bharat/IndicTrans2/tree/main