Starting this thread to share the progress on the Nepali LM and classification results @piotr.czapla @Moody
Repository: NLP for Nepali
Dataset
- Download Nepali Wikipedia Articles Dataset (38,757 articles) which I scraped, cleaned and used to train the language model
- Download Nepali News classification Dataset which I scraped and used to train the classifier
Results
Language Model
on 30% validation set
- Perplexity of language model: ~32
Classifier
- Accuracy of classification model: ~97%
- Kappa score of classification model: ~96
Pretrained Language Model
Download pretrained Language Model from here
Classifier
Download classifier from here
Tokenizer
Trained tokenizer using Google’s sentencepiece
Download the trained model and vocabulary from here