docs(sources): add HTR tooling survey — Kraken/eScriptorium, MiDRASH, HTR4PGP, Eynollah, dhSegment#34
Merged
Merged
Conversation
…, HTR4PGP, Eynollah Captures the layout-analysis and HTR tool landscape for historical Hebrew manuscripts. No data sources or source-index changes; doc-only. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
shaypal5
added
documentation
shaypal5
added a commit
that referenced
this pull request
May 31, 2026
- scripts/vision_transcribe.py: new script — sends all scan images to GPT-4o (vision, high-detail) with a Hebrew/Yiddish paleographer prompt; saves plain-text transcripts to data/transcripts/ and stamps each entry in entries.jsonl with status='raw', created_by='ocr', verification_status='unverified' - data/transcripts/: 186 new AI-draft .txt files covering NLI (Hannah Senesh diaries/notebook/pocket diary/speech), Wikimedia Commons letters, Library of Congress manuscripts, and the OPenn Zucker ketubah - data/index/entries.jsonl: transcription field added for all 186 entries; validation passes (198 entries) - scripts/review_app/app.py: four new routes — GET /transcripts (list with status filter tabs), GET /transcript/<id> (single-entry editor with prev/next nav), GET/POST /api/transcript/<id> (JSON read/write); saving promotes verification_status to primary_page_checked - scripts/review_app/templates/transcript_list.html: card grid with filter tabs (all/raw/reviewed/aligned/rejected/none), thumbnail previews, RTL snippet, status badges - scripts/review_app/templates/transcript_review.html: side-by-side scan viewer + RTL textarea editor; Ctrl+S saves, Ctrl+Enter approves, lightbox zoom, scan size toggle, reset-to-AI-draft; keyboard prev/next - scripts/review_app/templates/base.html: add Transcripts nav link - docs/transcripts_status.md: documents blockers and all sources tried Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Adds
docs/sources/chatgpt_summary_htr_tools.md— a planning reference doccapturing the open-source layout-analysis and HTR tooling landscape for
historical Hebrew manuscripts.
Why
The survey identified that several tools and pre-trained models are completely
absent from the project's planning docs, even though they directly apply to
material already in the corpus:
produces ALTO/PAGE-XML that slots into the existing
alto_path/hocr_pathentry-schema fields.
Kraken models for Cairo Genizah fragments, usable today against the T-S /
Halper items and the
openn__cairo_genizahcandidate.column layouts.
Changes
docs/sources/chatgpt_summary_htr_tools.md(new file, 117 lines)No changes to
data/index/, schemas, scripts, or tests — doc-only.🤖 Generated with Claude Code