sebastjan/reels-app
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Word-level extension: 2-word lookback (not full phrase)

Browse Source 
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).
This commit is contained in:
Sebastjan Artič 2026-04-29 16:52:44 +00:00
parent d73453fe50
commit d3b71942d2
1 changed files with 32 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
scripts/analyze.py
View File

@ -1436,27 +1436,50 @@ def main():
if all_words:
# Najdi "rob" — beseda kjer končanje zelo blizu clip start
# ALI clip start je sredi besede (besedo bi odrezali)
# ALI prejšnje besede so del istega govora pred clip start
# Strategija: poišči besedo PRED clip start, nato razširi nazaj
# za **1-2 besedi** (ne celo frazo - to bi zajelo prejšnji verz).
# Kombiniraj z amplitude defense (Layer 3) ki dodatno doda buffer.
MAX_LOOKBACK_WORDS = 2 # max 2 besedi nazaj
for i, w in enumerate(all_words):
# Beseda zaobsega clip start (clip reže sredi besede)
if w["start"] < current_start < w["end"]:
new_start = max(0, w["start"] - 0.15)
# Razširi nazaj na začetek te besede in največ MAX_LOOKBACK_WORDS predhodnih
anchor_idx = i
for j in range(i, max(0, i - MAX_LOOKBACK_WORDS), -1):
prev = all_words[j - 1]
curr = all_words[j]
gap = curr["start"] - prev["end"]
if gap >= 0.5:
break
anchor_idx = j - 1
new_start = max(0, all_words[anchor_idx]["start"] - 0.15)
captured = " ".join(w2["text"].strip() for w2 in all_words[anchor_idx:i+1])
print(f" 🎵 Razširim clip začetek {current_start:.2f}s → {new_start:.2f}s "
f"(clip rezal sredi besede '{w['text'].strip()}')", file=sys.stderr)
f"(clip sredi besede; ujamem '{captured}')", file=sys.stderr)
current_start = new_start
break
# Beseda končana TIK pred clip start (do 0.5s pred)
# IN je naslednja beseda PO/blizu clip start
if 0 < (current_start - w["end"]) <= 0.5:
# Preveri naslednjo besedo
next_w = all_words[i + 1] if i + 1 < len(all_words) else None
if next_w and next_w["start"] >= current_start - 0.1:
# Razdalja od te besede do naslednje > 0.3s pomeni mogoče prelom verz/refren
gap_to_next = next_w["start"] - w["end"]
# Razširi nazaj na začetek te besede - 0.15s buffer
new_start = max(0, w["start"] - 0.15)
# Najdi anchor: do MAX_LOOKBACK_WORDS nazaj
anchor_idx = i
for j in range(i, max(0, i - MAX_LOOKBACK_WORDS), -1):
prev = all_words[j - 1]
curr = all_words[j]
gap = curr["start"] - prev["end"]
if gap >= 0.5:
break
anchor_idx = j - 1
new_start = max(0, all_words[anchor_idx]["start"] - 0.15)
captured = " ".join(w2["text"].strip() for w2 in all_words[anchor_idx:i+1])
print(f" 🎵 Razširim clip začetek {current_start:.2f}s → {new_start:.2f}s "
f"(beseda '{w['text'].strip()}' končana {current_start - w['end']:.2f}s pred clip start, "
f"morda začne refren; gap do '{next_w['text'].strip()}' = {gap_to_next:.2f}s)", file=sys.stderr)
f"(beseda '{w['text'].strip()}' tik pred clip start; "
f"ujamem celo frazo '{captured}')", file=sys.stderr)
current_start = new_start
break
else: