Catalog

Overview of datasets, models, and tools for Slovak language processing.

The catalog serves as a central place where you can find existing resources for Slovak and use them in research or development.

Content is continuously updated in collaboration with the community.

SlovakBERT

Model
Contributors:
NLP KInIT
Gerulata
Modality
Text
Task
Fill-Mask
Language
sk
License
MIT
Open-source

Slovník slovenských pojmov

Tool
Contributors:
Modality
Text
Language
sk

Qwen3 14B SK

Model
Contributors:
Modality
Text
Domain
General Slovak language modeling
Task
Text Generation
Language
sk
License
Apache 2.0
Open-source

Slovak STS Synthetic

Dataset
Contributors:
Modality
Text
Task
Semantic Textual Similarity
Language
sk
License
CC-BY-NC-4.0
Open-source

skLEP

Dataset
Modality
Text
Task
POS, NER, RTE, NLI, STS, QA, text classification
Language
sk
License
Nekomerčné využitie
Open-source

Is your dataset, model, or tool missing here?