KInIT

Resources in the catalog18

• Whisper-large-v3-turbo-sk

  Model, speech and audio, MIT

  Slovak fine-tune of Whisper-large-v3-turbo.

  Transcribe speech

  NLP KInIT, KInIT

• FineWeb2 Slovak

  Dataset, text, ODC-By 1.0

  FineWeb2 Slovak is a comprehensive text corpus featuring over 14.1 billion words across 26.5 million documents tailored for Slovak natural language processing.

  Write in Slovak

  NLP KInIT

• E5-sk-large

  Model, text, MIT

  This is a specialized Slovak sentence-transformers model that maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic…

  Search by meaning

  LRKT FEI TUKE, NLP KInIT, NaiveNeuron FMPI CU

• E5-sk-small

  Model, text, MIT

  This is a specialized Slovak sentence-transformers model that maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic…

  Search by meaning

  LRKT FEI TUKE, NLP KInIT, NaiveNeuron FMPI CU

• SlovakBERT

  Model, text, MIT

  SlovakBERT is the first pretrained masked language model based on the RoBERTa architecture, optimized for Slovak natural language processing (NLP).

  Understand text

  NLP KInIT, Gerulata

• Dictionary of Slovak terms

  Tool, text

  A dictionary of Slovak terms linked into a single shared network.

  More resources

  NLP KInIT, eduself.sk

• Slovak STS Synthetic

  Dataset, text, CC BY-NC 4.0

  This is a synthetic Slovak dataset intended for the semantic textual similarity (STS) task.

  Search by meaning

  NLP KInIT

• skLEP

  Dataset, text, Nekomerčné využitie

  skLEP (General Language Understanding Evaluation benchmark for Slovak) is the first comprehensive benchmark specifically designed for evaluating Slovak natural language understanding (NLU)…

  Understand text

  LRKT FEI TUKE, NLP KInIT, NaiveNeuron FMPI CU