Bug: Claude picked clip start at 78.19s (0.3s before segment 'tepe' at
78.4s). Word-level extension then found word 'me' (77.88-78.16s) right
before clip start, extended to 77.73s. But the FULL phrase was 'Žena me'
where 'Žena' [76.88-77.74] precedes 'me' [77.88-78.16] in the same
breath/speech burst (gap 0.14s, not a real pause).
Fix: when extending back via word-level, do a lookback through earlier
words. Stop only when finding a real pause (gap >= 0.5s between words).
This captures the entire connected phrase before clip start.
Now: clip start 78.19s → finds 'me' at 78.16s → looks back: 'Žena' at
77.74s (gap to 'me' = 0.14s, < 0.5s) → continue. Earlier 'verjet.' at
76.78s (gap to 'Žena' = 0.10s) → also captured if connected... actually
'verjet.' is part of previous verse, but anchor stops at next pause >= 0.5s.
For the Žena case, anchor will be at 'Žena' (or earlier if no big pause).
This makes the extension MUCH more robust for cases where multiple words
of the chorus opening fall in the previous transcript segment.
Sebastjan Artič
49a80599e1