pycorrector

We have hosted the application pycorrector in order to run this application in our online workstations with Wine or directly.

Quick description about pycorrector:

Pycorrector is a Python toolkit for Chinese text error correction. It focuses on common error types such as similar-sounding characters, visually similar characters, grammar issues, proper noun errors, missing words, extra words, wrong words, and word-order problems. The project implements multiple correction approaches, including KenLM, ConvSeq2Seq, BERT, MacBERT, ELECTRA, ERNIE, GPT-style models, and newer Qwen-based correction models. It is designed for use cases such as input method correction, OCR correction, speech recognition cleanup, search query correction, and general Chinese proofreading. The repository includes usage examples, evaluation materials, datasets, documentation, and model references. It is useful for NLP engineers, researchers, and application developers building Chinese language quality tools.

Features:

• Chinese text error correction
• Phonetic and visual error handling
• Grammar and word-order correction
• KenLM and transformer model support
• Evaluation and dataset resources
• Ready-to-use Python toolkit

Programming Language: Python.
Categories: