wip: [01-stabilize] paused at task 1/1 - OCR Hallucination Immune logic via Semantic delta window and fret-isolation

This commit is contained in:
2026-03-29 22:08:40 +09:00
parent aca7bf592a
commit 2507de45d3
4289 changed files with 732689 additions and 28672 deletions

21
scripts/debug/dump_ocr.py Normal file
View File

@@ -0,0 +1,21 @@
import cv2
import sys
from pathlib import Path
from youtube_tab_to_pdf import extract_frames, extract_unique_overlay, _extract_number_above_bars
from video_cv_tracker import TemporalTracker
video_path = Path("output/サカナクション/新宝島(エレキギターTAB) 難易度★★★ sakanaction shintakarajima.mp4")
frames = extract_frames(video_path, fps=2.0)
print(f"Extracted {len(frames)} frames.")
# Tracker extracts raw pages
tracker = TemporalTracker(diff_threshold=0.03)
for frame in frames:
tracker.process_frame(frame)
pages = tracker.get_unique_pages()
print(f"Tracker found {len(pages)} unique pages.")
for i, page in enumerate(pages):
m_num = _extract_number_above_bars(page)
print(f"Page {i:03d} OCR Measure Num: {m_num}")