GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors
SOTA punctation restoration (for e.g. automatic speech recognition) deep learning model based on BERT pre-trained model
Code for chinese error detection module, using n-gram and bi-lstm
Pure Python Spell Checking http://pyspellchecker.readthedocs.io/en/latest/
The main features of barrust/pyspellchecker are: Text Correction.
Open-source alternatives to barrust/pyspellchecker include: mhagiwara/github-typo-corpus — GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors. nghuyong/text-correction-papers — text correction papers. nkrnrnk/bertpunc — SOTA punctation restoration (for e.g. automatic speech recognition) deep learning model based on BERT pre-trained model. zedom1/error-detection — Code for chinese error detection module, using n-gram and bi-lstm.
