Explore projects
-
lightweight JS-only slimmed down archive.org website prototype
Updated -
-
Updated
-
Tesseract deriver module used to OCR items with tesseract. Outputs hOCR and various metadata keys.
Updated -
Updated
-
Updated
-
Updated
-
Updated
-
-
Extract structured metadata and content from article PDFs; use this to match against databases of known identifiers.
Updated -
Automatic extraction data (e.g. content, title and etc) from archived news pages
Updated -
Updated
-
Updated
-
-
produces ffmpeg binary into a docker run-able nvidia runtime container that can run on GPU-enabled VMs/baremetals.
Updated -
-
This project is also mirror in github. https://github.com/internetarchive/dwebsummit-site
Updated -
-
-
Machine Learning applied to deskew and autocrop books and microfilm.
Contains tools to manage datasets, also contains actual ML scripts - using tensorflow and dhSegment
Updated