HHousen/DocSum

A tool to automatically summarize documents abstractively using the BART or PreSumm Machine Learning Model.

41
/ 100
Emerging

This tool helps busy professionals quickly grasp the core content of long documents. You provide it with a PDF or plain text, and it generates a concise summary. It's designed for anyone who needs to extract key information from lengthy reports, articles, or other textual content without reading every word.

No commits in the last 6 months.

Use this if you need to rapidly summarize individual documents or a collection of text files to understand their main points.

Not ideal if your PDFs have complex layouts with diverse font sizes and styles that don't clearly distinguish headings from body text, as it relies on font properties to structure content.

document-analysis research-review information-extraction content-briefing report-digestion
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

69

Forks

13

Language

Python

License

GPL-3.0

Last pushed

Nov 23, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/HHousen/DocSum"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.