wordninja 2.0.0

Probabilistically split concatenated words using NLP based on English Wikipedia uni-gram frequencies

07-15-2023 111 words One minute 0 views

Contents

Probabilistically split concatenated words using NLP based on English Wikipedia uni-gram frequencies.

Stars: 864, Watchers: 864, Forks: 112, Open Issues: 19

The keredson/wordninja repo was created 8 years ago and the last code push was 2 years ago.
The project is popular with 864 github stars!

You can install wordninja using pip

pip install wordninja

or add it to a project with poetry

poetry add wordninja

No wordninja pypi packages just yet.

A list of common wordninja errors.

Here are some wordninja code examples and snippets.

Spelling Corrector

Convert number words eg. three hundred and forty two to numbers (342).

BERT

OCR-free Document Understanding Transformer

Embeddings, Retrieval, and Reranking

Simple inference for large language models

Logging utilities for SpaCy

Neural Networks Compression Framework

Python client for the NLP Cloud API