segment-any-text/wtpsplit
Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.
This tool helps you break down large blocks of text into individual sentences or paragraphs, making it easier to analyze or process. You input raw text, and it outputs a list of cleanly separated sentences or paragraphs. Anyone who works with text data, such as researchers, content analysts, or data scientists, can use this to prepare text for further tasks like translation, summarization, or information extraction.
1,255 stars. Used by 1 other package. Available on PyPI.
Use this if you need to reliably split text into meaningful, distinct sentences or paragraphs, especially across many languages or diverse text styles.
Not ideal if you only need very basic punctuation-based sentence splitting for a single language, as simpler tools might suffice.
Stars
1,255
Forks
82
Language
Python
License
MIT
Category
Last pushed
Feb 26, 2026
Commits (30d)
0
Dependencies
8
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/segment-any-text/wtpsplit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
nltk/nltk
NLTK Source
explosion/spaCy
💫 Industrial-strength Natural Language Processing (NLP) in Python
undertheseanlp/underthesea
Underthesea - Vietnamese NLP Toolkit
stanfordnlp/stanza
Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many...
flairNLP/flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)