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.

MiniMax-M3

Model
Contributors:
MiniMax
Modality
Other
Language
sk, eng, other

BGE-M3

Model
Contributors:
University of Science and Technology of China
BAAI
Modality
Text
Language
sk, eng, other
Open-source

ANLI SK

Dataset
Contributors:
Modality
Text
Domain
General
Task
Natural language inference
Language
sk
License
CC-BY-NC-SA 4.0
Open-source

MultiSocial

Dataset
Contributors:
Modality
Text
Domain
News
Task
Machine-generated text detection
Language
sk and other
Gated access

skMTEB

Dataset
Contributors:
SlovakNLP Community
Modality
Text
Domain
Other
Task
Benchmarking
Language
sk
License
CC-BY-4.0

SloPalSpeech

Dataset
Contributors:
Modality
Speech/audio
Domain
Politics
Task
Automatic Speech Recognition
Language
sk
License
CC-by-4.0

GEST

Dataset
Contributors:
Modality
Text
Domain
General
Task
Gender stereotypical reasoning and translation
Language
eng, sk, by, hrv, cz, pl, rus, srb, si, ua
License
Apache 2.0

Whisper-large-v3-sk

Model
Contributors:
Modality
Speech/audio
Task
Automatic Speech Recognition
Language
sk
License
apache-2.0

Whisper-large-v3-turbo-sk

Model
Contributors:
Modality
Speech/audio
Task
Automatic Speech Recognition
Language
sk
License
mit

Is your dataset, model, or tool missing here?