metadata

language:
  - la
tags:
  - latin
  - token-classification
  - pos
  - dependency-parsing
base_model: ClassCat/roberta-base-latin-v2
datasets:
  - universal_dependencies
license: cc-by-sa-4.0
pipeline_tag: token-classification
widget:
  - text: deus videt te non sentientem

roberta-base-latin-ud-goeswith

Model Description

This is a RoBERTa model pre-trained on CC-100 Latin texts for POS-tagging and dependency-parsing (using goeswith for subwords), derived from roberta-base-latin-v2.

How to Use

from transformers import pipeline
nlp=pipeline("universal-dependencies","KoichiYasuoka/roberta-base-latin-ud-goeswith",trust_remote_code=True,aggregation_strategy="simple")
print(nlp("deus videt te non sentientem"))