This repository contains State of the Art Language models and Classifier for Odia, which is spoken in the Indian state of Odisha.
The models trained here have been used in Natural Language Toolkit for Indic Languages (iNLTK)
Architecture/Dataset | Odia Wikipedia Articles |
---|---|
ULMFiT | 26.57 |
TransformerXL | 26.81 |
Dataset | Accuracy | Kappa Score |
---|---|---|
Odia News Dataset | 95.52 | 93.02 |
Architecture | Visualization |
---|---|
ULMFiT | Embeddings projection |
TransformerXL | Embeddings projection |
Download pretrained Language Model from here
Download classifier from here
Trained tokenizer using Google's sentencepiece
Download the trained model and vocabulary from here