Open Issues Need Help
View All on GitHub help wanted urdu-language lexicon
A modern, dependency-free NLP toolkit for Urdu — normalization, tokenization, stopwords, stemming and Roman Urdu transliteration. No TensorFlow, no model downloads, no dependencies.
Python
#low-resource-languages#natural-language-processing#nlp#python#roman-urdu#text-processing#tokenization#transliteration#urdu#zero-dependency
Tokenizer: recover omitted spaces after non-joining letters about 3 hours ago
help wanted
A modern, dependency-free NLP toolkit for Urdu — normalization, tokenization, stopwords, stemming and Roman Urdu transliteration. No TensorFlow, no model downloads, no dependencies.
Python
#low-resource-languages#natural-language-processing#nlp#python#roman-urdu#text-processing#tokenization#transliteration#urdu#zero-dependency
Verify the 118 existing lexicon entries (~8% are estimated wrong) about 3 hours ago
help wanted good first issue urdu-language lexicon
A modern, dependency-free NLP toolkit for Urdu — normalization, tokenization, stopwords, stemming and Roman Urdu transliteration. No TensorFlow, no model downloads, no dependencies.
Python
#low-resource-languages#natural-language-processing#nlp#python#roman-urdu#text-processing#tokenization#transliteration#urdu#zero-dependency
Add missing common words to the transliteration lexicon about 3 hours ago
help wanted good first issue urdu-language lexicon
A modern, dependency-free NLP toolkit for Urdu — normalization, tokenization, stopwords, stemming and Roman Urdu transliteration. No TensorFlow, no model downloads, no dependencies.
Python
#low-resource-languages#natural-language-processing#nlp#python#roman-urdu#text-processing#tokenization#transliteration#urdu#zero-dependency