Metric: indic_glue
Update on GitHub


IndicGLUE is a natural language understanding benchmark for Indian languages. It contains a wide variety of tasks and covers 11 major Indian languages - as, bn, gu, hi, kn, ml, mr, or, pa, ta, te.

How to load this metric directly with the datasets library:

from datasets import load_metric
metric = load_metric("indic_glue")


    title={{IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages}},
    author={Divyanshu Kakwani and Anoop Kunchukuttan and Satish Golla and Gokul N.C. and Avik Bhattacharyya and Mitesh M. Khapra and Pratyush Kumar},
    booktitle={Findings of EMNLP},