tts-voice-creator-clone-and.../VERSION
mARTin-B78 a78dac98fa
Some checks are pending
Test and SonarQube / quality (push) Waiting to run
fix(magazine): catch vision OCR decoding loops before they become page text
Confirmed live: re-ingesting c't KI Wissen 2026 with a local Qwen VL
engine, page 18's chart transcription degenerated into "das Produkt,
das Produkt, das Produkt, ..." repeated hundreds of times, filling the
whole response budget -- and was accepted as real region text, which
would have been narrated verbatim.

The codebase already had two narrow signatures for specific observed
failures (a formatting-instruction echo, a fabricated LaTeX loop), both
scoped to the plain-text fallback path only. Added a general detector
(_looks_like_repetition_loop): any short phrase containing a real word,
repeated 8+ times immediately back-to-back. Deliberately excludes
patterns with no letters -- a dot-leader contents line, a repeated
number sequence -- which are legitimate and must not be flagged.

Applied at both call sites: vision_ocr_page (the labelled-region path
most engines use) and _whole_page_region (the plain-text fallback).
Treated as a failed call in both, so vision_ocr_page_chain's existing
fallback (secondary engine, then tesseract) gets a real chance instead
of garbage being accepted as the page's transcription.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-09-13 10:09:32 +02:00

1 line
6 B
Plaintext