Use HeOCR
What to use today to get Hebrew text out of documents.
heocr · the pipeline
Hebrew text, headings and tables out of any document: PDF, Word, Excel, PowerPoint, web pages and scans. It reads a PDF's own text layer where it can be trusted and runs OCR where it can't, and it records which, page by page, along with anything it could not read. pip install heocr (on PyPI from version 0.1.0; until then, install from the repository).
R7 · OCR for old printed Hebrew
Our recommended OCR model for scanned books and older print. Not measured on a held-out set yet: the historical-print test set is waiting for volunteer references. Use it in heocr with --ocr-model heocr_r7, or in Tesseract with -l heocr_r7.
Earlier models and research baselines stay openly available on Hugging Face and Zenodo.
Datasets
Each dataset is built only from material that can be redistributed and reused, including for machine learning. Rights are recorded for each item, not assumed for a whole collection.
HASH
Hebrew Archive of Scanned Handwriting: scanned handwritten Hebrew-script documents from the 18th century onward, including letters, notebooks, drafts and forms.
htext
Public-domain Hebrew text for training, starting with lines from Project Ben-Yehuda works, plain and with niqqud. Each work is flagged as public domain in Israel and/or the US.
hletterscript
Cropped handwritten Hebrew letters, grouped by writer and taken from public-domain scans. Used to make synthetic handwriting.
HeOCR & HeOCRsynth
The main OCR/HTR datasets: one mixing real and synthetic pages, and one synthetic only. Both are exported by hocrgen once its release checks pass.
Sources & credit
We use public-domain works only, and each item keeps its source and credit. See rights & takedown for how rights are checked.
National Library of Israel
Scans of public-domain books from its "public domain, free use" collection. Credited on every item as "From the collections of the National Library of Israel / מאוסף הספרייה הלאומית", with the record number.
Internet Archive & Wikimedia Commons
Public-domain book scans made by university libraries, such as the University of Toronto, and by Google for libraries. Each item keeps its identifier, who scanned it and its rights evidence. Google's cover pages and watermarks are removed.
Project Ben-Yehuda
Volunteer-typed, public-domain texts of the same editions. They supply the exact text for each scanned line, and the training text for synthetic pages.
Hebrew Wikisource
Proofread transcriptions of scanned pages. We use them for evaluation, with each page checked by a human. Their text is CC BY-SA.
Generators & pipelines
The code that builds the datasets and trains the models. All of it is MIT-licensed.
hocrsyngen
Synthetic Hebrew page generator. It renders printed and handwriting-style pages, with line annotations and right-to-left metadata, from CC0 training text and open fonts.
hletterscriptgen
Extracts per-writer letter sets from HASH scans and human-reviewed glyph annotations.
hocrgen
Dataset operations and release checks: acquisition, rights, review, deduplication, splits, benchmarks and export to the public datasets.
heocr-engine
Training, evaluation and release code for the models above, plus a local Tesseract baseline with a reproducible prediction format.
Code signing policy
For the HeOCR desktop app.
Windows: free code signing provided by SignPath.io, certificate by SignPath Foundation. Only installers built by GitHub Actions from the public source are signed, and each signing is approved by hand. macOS: signed with an Apple Developer ID and notarized by Apple.
Team roles: committers and reviewers, Shay Palachy Affek (@shaypal5), with AI coding agents that work through reviewed pull requests; approver, Shay Palachy Affek.
Privacy: this program will not transfer any information to other networked systems unless specifically requested by the user or the person installing or operating it. The app has no network feature at all. The full policy.