DiacNetIg

GitHub Repository

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.

Model Details

  • Model Type: Syllable/Character-level k-NN with Context Backoff
  • File Size: 342 KB (igbo_diacritizer.json)
  • Supported Languages: Igbo (ig)
  • Metrics:
    • Word Accuracy: 88.10% (evaluated on 54,162 words)
  • Dependencies: None (pure Python / zero dependencies)

Usage

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"

Links

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including olaverse/diacnet-ig