hunaccent
Diacritic restorer
A C++ library that uses machine learning to restore diacritics in Hungarian text
Accentize Hungarian text
15 stars
3 watching
1 forks
Language: C++
last commit: about 2 years agoLinked from 1 awesome list
oroszgy/awesome-hungarian-nlpRelated projects:
| Repository | Description | Stars |
|---|---|---|
 aielte-research/diacritics_restoration | A Python-based framework for training and evaluating diacritics restoration models using lightweight 1D convolutional neural networks | 4 |
 attilanagy234/neural-punctuator | An implementation of BERT-based models for automatic punctuation restoration in English and Hungarian texts. | 48 |
 cisocrgroup/pocoto | A Java-based tool for correcting errors in OCR'd historical documents | 40 |
 algolzw/daclip-uir | This project controls vision-language models to restore degraded images in various environments and conditions. | 673 |
 huspacy/huspacy | An industrial-strength natural language processing library for Hungarian language text analysis | 158 |
 nytud/hucola | A collection of 9,076 annotated sentences in Hungarian to evaluate linguistic acceptability and grammaticality | 1 |
 jecisc/chanel | A tool for cleaning and improving Smalltalk code | 22 |
 kuhumcst/cstlemma | A lemmatiser tool for multiple languages using affix rules and supervised learning from full-form dictionaries. | 36 |
 hamdikahloun/windows_ocr | An OCR library allowing developers to embed high-quality character recognition functionality in their products. | 18 |
 alvenirai/punctfix | A Python library that adds punctuation and capitalization to text without punctuation. | 23 |
 patois/xray | Tool for filtering and highlighting decompiler output based on regular expressions | 125 |
| cisocrgroup/resources | Resources and data for developing a language-aware OCR document error profiler and PoCoTo tools. | 15 |
 yaacov/hebocr | A Hebrew character recognition library | 5 |
 hodefoting/kernagic | A semi-automatic font spacing tool that allows users to interactively adjust the spacing between glyphs in a UFO font. | 75 |
 poltextlab/hunempoli_corpus | A manually annotated corpus for training and testing machine learning models of Aspect Based Sentiment Analysis (ABSA) in Hungarian language. | 0 |