DiacNet
Collection
5 items • Updated
DiacNetIg is a lightweight dot-below diacritics restorer for Igbo (ig) text. It restores dot-below marks (ọ, ụ, ị, ẹ) using a character-level k-NN backoff classifier.
igbo_diacritizer.json)ig)Loaded and used via the unified olaverse SDK wrapper:
from olaverse.nlp.diacritizer import Diacritizer
diacritizer = Diacritizer(model="diacnet-ig")
text = "Kedu ka i mere taa"
print(diacritizer.restore(text))
# Output: "Kedụ ka ị mere taa"