README.md

metadata

library_name: spacy
metrics:
  - accuracy
pipeline_tag: token-classification

NER for Early New High German (Frühneuhochdeutsch)

Based on the SpaCy German model and trained on letters from the Bullinger collection

How to use

import spacy
nlp = spacy.load('./enhg-ner')
doc = nlp('Ich hab euch uff gestert ouch by ainem mennlin von Strasburg geschriben mitt ainem brieff gen Bern gehörig.')
for ent in doc.ents:
  print(ent.text, ent.label_)

# Output:
# Strasburg GEO
# Bern GEO