reels-app/scripts
Sebastjan Artič d3b71942d2 Word-level extension: 2-word lookback (not full phrase)
Refinement of previous lookback fix - limit to MAX 2 words back.

Reason: with unlimited lookback, the lookback would chain through
words with gaps < 0.5s and keep walking back into the previous verse.
For Žena ME TEPE: 'verjet.' [76.78] → 'Žena' [76.88] gap is 0.10s,
which means lookback would walk back to verses before chorus.

With 2-word limit:
- Clip at 78.19s → 'me' [78.16] is closest preceding word (gap 0.03s)
- Lookback j=i: 'me' → 'Žena' gap 0.14s → captured (i-1)
- Lookback j=i-1: 'Žena' → 'verjet.' gap 0.10s → would be captured
  but MAX_LOOKBACK_WORDS=2 stops here ✓

Result: anchor = 'Žena' at 76.88s → new_start = 76.73s.
Subtitle: 'ŽENA ME TEPE' (full phrase, no verse leakage).
2026-04-29 16:53:29 +00:00
..
acr_recognize.py MXF/MPG broadcast format support: handle multichannel audio properly 2026-04-29 14:38:48 +00:00
analyze.py Word-level extension: 2-word lookback (not full phrase) 2026-04-29 16:53:29 +00:00
clip.py Upgrade default Whisper model: small/medium → large-v3 for much better Slovenian/Slavic transcription accuracy 2026-04-29 08:20:18 +00:00
find_chorus.py Find chorus: weight repetitive short phrases (like 'Ohne dich x5') as strong chorus signal 2026-04-28 16:57:45 +00:00
reframe.py MXF/MPG broadcast format support: handle multichannel audio properly 2026-04-29 14:38:48 +00:00
subtitle.py Upgrade default Whisper model: small/medium → large-v3 for much better Slovenian/Slavic transcription accuracy 2026-04-29 08:20:18 +00:00
yt_download.py Add cookies support to yt_download.py for YouTube bot detection bypass 2026-04-28 15:47:59 +00:00