Sinhala-CharBERT Seq2Seq Typo Corrector

Open-vocabulary seq2seq typo corrector for Sinhala. Dual-channel (subword + phonological akshara) encoder with an autoregressive akshara-level Transformer decoder. Designed as the optional neural backend (neural_backend="seq2seq" | "hybrid") of sinlib's TypoDetector.

Usage

from sinlib import TypoDetector

detector = TypoDetector(neural_backend="hybrid")  # uses this repo by default
print(detector("මම ගෙදර යන්ඩ ඕනේ"))   # මම ගෙදර යන්න ඕනේ
print(detector("මම gedara යන්න ඕනේ")) # මම ගෙදර යන්න ඕනේ
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 Ransaka/sinhala-charbert-seq2seq