metadata
license: apache-2.0
language: ga
tags:
- irish
BERTreach
(beirtreach means 'oyster bed')
Model size: 84M
Training data:
- PARSEME 1.2
- Newscrawl 300k portion of the Leipzig Corpora
- Private news corpus crawled with Corpus Crawler
(2125804 sentences, 47419062 tokens, as reckoned by wc)
from transformers import pipeline
fill_mask = pipeline("fill-mask", model="jimregan/BERTreach", tokenizer="jimregan/BERTreach")