Adding fix to the word position that the logo begins

gnommo/transformer.py

@@ -412,6 +412,40 @@ def _find_phrase_timestamp(
     return -1, -1.0, 0.0, -1
 
 
+# Pause-variant video marker prefixes (e.g. [vftp:logo]). These freeze the
+# narration when they fire, so their start must land in the gap BETWEEN words,
+# never mid-word — otherwise the narration cuts out half-way through a word and
+# finishes it when the video ends.
+_PAUSE_MARKER_PREFIXES = (
+    "vftp:", "vfbp:", "vfmp:",
+    "vf2tp:", "vf2bp:", "vf2mp:",
+    "vstp:", "vsbp:", "vsmp:",
+)
+
+
+def _snap_to_word_gap(t: float, transcription: list) -> float:
+    """Snap a time to the midpoint of the gap between transcript words.
+
+    - t inside a word  → midpoint of the gap AFTER that word (the word finishes,
+      then the pause begins), or the word's end if it's the last word.
+    - t already in a gap → midpoint of that gap.
+    - t before the first / after the last word → unchanged.
+    """
+    if not transcription:
+        return t
+    n = len(transcription)
+    for i, w in enumerate(transcription):
+        if w.start <= t <= w.end:
+            nxt = transcription[i + 1] if i + 1 < n else None
+            return round((w.end + nxt.start) / 2, 3) if nxt else round(w.end, 3)
+        if w.start > t:
+            if i == 0:
+                return t
+            prev = transcription[i - 1]
+            return round((prev.end + w.start) / 2, 3)
+    return t
+
+
 def align_markers_to_transcription(
     manuscript_text: str,
     transcription: list[TranscribedWord],
@@ -623,6 +657,16 @@ def align_markers_to_transcription(
                     confidence=timing.confidence,
                 )
 
+    # Snap pause-narration video markers off any word they land inside, to the
+    # midpoint of the gap after it — so the freeze happens between words, not
+    # mid-word. Flows into both the render plan and events.json.
+    if transcription:
+        for timing in deduped:
+            if timing.timestamp >= 0 and timing.marker_id.startswith(
+                _PAUSE_MARKER_PREFIXES
+            ):
+                timing.timestamp = _snap_to_word_gap(timing.timestamp, transcription)
+
     return deduped