Skip to main content
digdir emblemdata.norge.no
Find dataShare data
Nasjonalbiblioteket

NB BERT-base

Description

NB BERT-base is a general BERT-base model built on the large digital collection at the National Library of Norway. The model is based on the same structure as BERT Cased multilingual model, and is trained on a wide variety of Norwegian text - both Bokmål and Nynorsk - from the last 200 years.

Version 1.1 of the model is general, and should be fine-tuned for any particular use.

NB BERT-base has been produced and released by the AI-lab at the National Library of Norway, and is one of the best performing models for Norwegian and other Scandinavian languages yet.

Distributions
1

Download
Description:
Not provided
Access URL:
https://hdl.handle.net/21.11146/72
Direct download:
Not provided
API:
Not provided
Documentation:
Not provided
License:
https://creativecommons.org/licenses/by/4.0/
Conforms to:
Not provided

APIs providing this dataset
0

No registered APIs provide this dataset.

Similar datasets

Norsk Ordbank - Norwegian Nynorsk 2005-2012Nasjonalbiblioteket
Public access
ONOMASTICA Pronunciation Lexicon 2Nasjonalbiblioteket
Public access
Translation Memories from Semantix ASNasjonalbiblioteket
Public access
Grapheme-to-Phoneme Models for NorwegianNasjonalbiblioteket
Public access
SCARRIE LexiconNasjonalbiblioteket
Public access