metadata
license: agpl-3.0
datasets:
- vesteinn/FC3
- vesteinn/IC3
- mideind/icelandic-common-crawl-corpus-IC3
- DDSC/partial-danish-gigaword-no-twitter
- NbAiLab/NCC
widget:
- text: Býir vaksa <mask> enn nakað annað búøki á jørðini.
language:
- fo
This is a Faroese language model, it was trained by adapting the ScandiBERT-no-faroese model on the FC3 corpus for 50 epochs.
If you find this model useful, please cite
@inproceedings{snaebjarnarson-etal-2023-transfer,
title = "{T}ransfer to a Low-Resource Language via Close Relatives: The Case Study on Faroese",
author = "Snæbjarnarson, Vésteinn and
Simonsen, Annika and
Glavaš, Goran and
Vulić, Ivan",
booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = "may 22--24",
year = "2023",
address = "Tórshavn, Faroe Islands",
publisher = {Link{\"o}ping University Electronic Press, Sweden},
}