Tokenization & Preprocessing
hunspell/hunspell🔥 active
▲ +1 ★ this week
The most popular spellchecking library.
🧠 Natural Language Processing
C++LGPL-2.1updated Nov 13, 2026
🏆 #5,727 overall#142 of 178 in Tokenization & Preprocessing
words /stemmer
Fast Porter stemmer implementation
$ git clone https://github.com/words/stemmer.gitStars
137
137
This week
—
Forks
8
8
Language
JavaScript
License
MIT
Created
Jun 13, 2014
12.4 years old
Last push
Nov 2, 2022
Categories
GitHub topics
More in Tokenization & Preprocessing
Tokenization & Preprocessing
anujvyas/Natural-Language-Processing-Projects
This repository consists of all my NLP Projects
🧠 Natural Language Processing💖 Sentiment Analysis🗂️ Text Classification
Jupyter Notebookno licenseupdated Nov 10, 2020
Tokenization & Preprocessing
biolab/orange3-text
🍊 :page_facing_up: Text Mining add-on for Orange3
💎 Text Mining💖 Sentiment Analysis🧠 Natural Language Processing
PythonOtherupdated Oct 27, 2026
Tokenization & Preprocessing
ropensci/hunspell
High-Performance Stemmer, Tokenizer, and Spell Checker for R
C++Otherupdated Feb 12, 2026
Tokenization & Preprocessing
rasbt/LLMs-from-scratch🔥 active
▲ +435 ★ this week
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
🤖 Language Models🧠 Natural Language Processing
Jupyter NotebookOtherupdated Nov 9, 2026
Tokenization & Preprocessing
explosion/spaCy
▲ +18 ★ this week
💫 Industrial-strength Natural Language Processing (NLP) in Python
🧠 Natural Language Processing🏷️ Named Entity Recognition🗂️ Text Classification
PythonMITupdated Oct 27, 2026
Data from GitHub · snapshot Nov 13, 2026