Natural Language Toolkit
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML.
An accurate natural language detection library, suitable for short text and mixed-language text
A library for Unicode normalization (NFC, NFD, NFKC, NFKD) independent of Python's core Unicode database.
🦛 CHONK your texts with Chonkie ✨ - The no-nonsense chunking library
Thai Natural Language Processing library
Generalist model for NER (Extract any entity types from texts)
Microsoft Azure Text Analytics Client Library for Python
uroman is a universal romanizer. It converts text in any script to the standard Latin alphabet.
Pyap is an MIT Licensed text processing library, written in Python, for detecting and parsing addresses. Currently it supports USA, Canadian and British addresses.
Textile processing for python.
Unsupervised Korean Natural Language Processing Toolkits
Functions to preprocess and normalize text.
Extract quantities from unstructured text.
High-performance document intelligence library for Python. Extract text, metadata, and structured data from PDFs, Office documents, images, and 88+ formats. Powered by Rust core for 10-50x speed improvements.
Text extraction library for typical file formats found in SharePoint repositories
Onnx Text Recognition (OnnxTR): docTR Onnx-Wrapper for high-performance OCR on documents.
The goal of the Indic NLP Library is to build Python based libraries for common text processing and Natural Language Processing in Indian languages.
an extensible tool to process legal citations in text
Module for automatic summarization of text documents and HTML pages.
Natural language processing augmentation library for deep neural networks
NeMo text processing for ASR and TTS
A base class for wrapping text-processing tools
Wrappers for several pre-processing scripts from the Moses toolkit.
NLP, before and after spaCy
Collection of stopwords for multiple languages, using ISO 639-1 language code.
Natural Language Processing (NLP) library for Urdu language.
Python package for Korean natural language processing.
Generalist and Lightweight Model for Text Classification
Python library for processing Chinese text
PyRuSH is the python implementation of RuSH (Rule-based sentence Segmenter using Hashing), which is originally developed using Java. RuSH is an efficient, reliable, and easy adaptable rule-based sentence segmentation solution. It is specifically designed to handle the telegraphic written text in clinical note. It leverages a nested hash table to execute simultaneous rule processing, which reduces the impact of the rule-base growth on execution time and eliminates the effect of rule order on accuracy.
Breame is a lightweight Python package with a number of tools to aid in the detection of words that have dual spellings and meanings in British and American English.
A Python library for a _FULL_ Zalgo experience
A high-performance library for computational linguistics
Onnx Text Recognition (OnnxTR) OCR plugin for docling
Low-precision BF16/FP16 deep learning optimizer (LuminaV) and text data processing engine with native Rust SIMD, Vulkan, and Triton acceleration.
A text summarization and keyword extraction package based on TextRank
A minimalist collection of text processing tools for Python 3
Generalist model for Relation Extraction (Extract any relation types from texts)
A fast, compact pure-Python tokenizer for Icelandic text with sentence segmentation
Text processing utilities for scientific workflows — LaTeX formatting, colored output, string parsing, and plot text helpers
Fast CPU/GPU ONNX inference for GLiNER, GLiNER2, GLiClass, GLiFormer, and System One.
HuSpaCy: industrial strength Hungarian natural language processing