poison-flower/pf-ocr
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ocr): unify config, add manga translation pipeline and context lookahead

Browse Source 
- Consolidate module configs into root config.example.json with ocr, vision, and epub sections

- Split LLM OCR workflows into novel_ocr.py (prose) and manga_ocr_llm.py (manga)

- Remove gemini_direct_ocr.py in favor of OpenAI-compatible API endpoints

- Support direct manga translation via --translate, --target-lang, and glossary.md

- Add bidirectional context support: past translations (--context-pages) and lookahead Japanese text (--context-pages-ahead)

- Add per-page JSON audit logging under logs/ and expose OpenAI sampling parameters
This commit is contained in:
Poison Flower
2026-09-06 15:42:29 +03:00
parent 41c6e97cd4
commit 35b7be680e
23 changed files with 1811 additions and 494 deletions
Download Patch File Download Diff File Expand all files Collapse all files
epub_builder/furigana.py
+1 -1
View File
@@ -1,6 +1,6 @@
#!/usr/bin/env python3
"""
Shared logic for turning OCR page text (see ocr/prompt.txt for the expected
Shared logic for turning OCR page text (see ocr/prompt_novel.txt for the expected
format) into HTML paragraphs, including furigana rendered as proper <ruby>
markup. Used by build_epub.py, and also runnable standalone as a quick
preview/debugging tool for a single page.