Ransaka/sinhala-charbert-seq2seq

🤗 Hugging Face 来源mit701 MBother✓ 1 个校验和今天更新

一条命令提交

在你的模型文件夹旁边运行它。它会制作种子、将文件与 Hugging Face 比对，然后提交。你只需开始做种，并粘贴你账户中的密钥。它只读取你的文件，绝不修改。如果愿意，可以先阅读脚本。

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo Ransaka/sinhala-charbert-seq2seq ./model-folder

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