metadata
language: si
license: mit
tags:
- sinhala
- typo-correction
- charbert
- seq2seq
- sinlib
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