This repository contains classifier to distinguish which Indian Language a given text contains.
The following languages are supported:
| Language |
|---|
| Hindi |
| Punjabi |
| Sanskrit |
| Gujarati |
| Kannada |
| Malyalam |
| Nepali |
| Odia |
| Marathi |
| Bengali |
| Tamil |
| Urdu |
You can download the dataset on which model was trained from here.
Scripts to prepare the dataset can be found in dataset-preparation folder.
The classifier has 99% accuracy!
You can download the trained classifier from here.
You can download the tokenizer and vocab from here.