Skip to main content

sumbert: A BERT-based summarizer with a frindly API

Project description

Abstractive BERT-based Text Summarizer

A BERT-based summarizer, centered towards a simple API: some text in, a summary out, both strings. Also at pypi.org as package sumbert.

Installation:

pip3 install sumbert

or if you want ot play with the code, after cloning this, and going into the resulting folder, install as an editable package with:

pip3 install -e .

Usage:

$ python3 -i
>>> from sumbert import summarize
>>> 
>>> text= """... your favorite story ..."""
>>> print(summarize(text))

This package is designed as a simple API for an otherwise fairy intricate set of components.

Credits:

The code is derived from the bertabs submodule in the HuggingFace transformers package at

https://github.com/huggingface/transformers

which credits the abstractive summarization described in the article Text Summarization with Pretrained Encoders by Yang Liu and Mirella Lapata.

The original code described in the article can be found on the Yang Liu's github repository.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sumbert-1.0.0.tar.gz (16.5 kB view hashes)

Uploaded source

Built Distribution

sumbert-1.0.0-py3-none-any.whl (21.5 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page