README.md

metadata

language: cs
tags:
  - Czech
  - RoBERTa
  - ÚFAL
license: cc-by-nc-sa-4.0

RobeCzech model

RobeCzech is a monolingual RoBERTa language representation model trained on Czech data.

RobeCzech model is released publicly at LINDAT and Hugging Face.

Please cite the corresponding publication:

• Milan Straka, Jakub Náplava, Jana Straková and David Samuel: Czech RoBERTa, a monolingual contextualized language representation model. Accepted to TSD 2021.

Preprint of the paper is available at https://arxiv.org/abs/2105.11314.