< Python

Share Share Share

Awesome Python NLP

• allennlp 11,751

  

  | updated about 2 years ago | Apache License 2.0

  An open-source NLP research library, built on PyTorch.

• bert 37,769

  

  | updated 4 months ago | Apache License 2.0

  TensorFlow code and pre-trained models for BERT

• contractions 308

  

  | updated about 2 years ago | MIT License

  Fixes contractions such as `you're` to `you are`

• fuzzywuzzy 9,191

  

  | updated almost 2 years ago | GNU General Publi...

  Fuzzy String Matching in Python

• gensim 15,622

  

  | updated 3 months ago | GNU Lesser Genera...

  Topic Modelling for Humans

• haystack 14,953

  

  | updated 4 months ago | Apache License 2.0

  🔍 LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

• nltk 13,395

  

  | updated 3 months ago | Apache License 2.0

  NLTK Source

• polyglot 2,312

  

  | updated about 1 year ago | Other

  Multilingual text (NLP) processing toolkit

• sentence-transformers 15,213

  

  | updated about 1 month ago | Apache License 2.0

  State-of-the-Art Text Embeddings

• spaCy 29,546

  

  | updated 4 months ago | MIT License

  💫 Industrial-strength Natural Language Processing (NLP) in Python

• stanza 7,278

  

  | updated about 1 month ago | Other

  Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

• transformers 133,705

  

  | updated about 1 month ago | Apache License 2.0

  🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

• whatthelang 165

  

  | updated over 5 years ago | Apache License 2.0

  Lightning Fast Language Prediction 🚀

• wikiextractor 3,738

  

  | updated 6 months ago | GNU Affero Genera...

  A tool for extracting plain text from Wikipedia dumps

• word_cloud 10,101

  

  | updated 3 months ago | MIT License

  A little word cloud generator in Python