metadata
language:
- uk
tags:
- token-classification
- punctuation prediction
- punctuation
library_name: generic
license: mit
metrics:
- f1
Ukrainian model to restore punctuation and capitalization
This is the NeMo model to restore punctuation and capitalization in sentences, trained on 10m+ sentences from UberText 2.0 corpus (yet unreleased). Basic transformer under the hood is bert-base-multilingual-cased
.
Model restores the following punctuations -- [? . ,].
It also restores capitalization of words.
Copyright: Dmytro Chaplynskyi, lang-uk project, 2022