chore: atualização geral

code/fcpxml/transcribe.py

@@ -16,7 +16,7 @@ import logging
 import os
 import re
 from pathlib import Path
-from typing import List, Optional, Sequence, Tuple
+from typing import Callable, List, Optional, Sequence, Tuple
 
 logger = logging.getLogger(__name__)
 
@@ -118,7 +118,10 @@ def invert_ranges(
 
 
 def transcribe(
-    path: str, model_size: str = "base", language: Optional[str] = None
+    path: str,
+    model_size: str = "base",
+    language: Optional[str] = None,
+    progress_cb: Optional[Callable[[float], None]] = None,
 ) -> Optional[dict]:
     """Transcribe an audio/video file locally with word-level timestamps.
 
@@ -170,6 +173,10 @@ def transcribe(
         )
         segments: List[dict] = []
         words: List[dict] = []
+        # `info.duration` is known upfront (from the container), so each
+        # segment's end time — yielded lazily as faster-whisper decodes —
+        # gives real, granular progress instead of a single before/after step.
+        total_duration = float(info.duration) if info.duration else 0.0
         for seg in segments_iter:
             start = float(seg.start)
             end = float(seg.end)
@@ -182,6 +189,8 @@ def transcribe(
                     "end_fmt": format_timestamp(end),
                 }
             )
+            if progress_cb is not None and total_duration > 0:
+                progress_cb(min(end / total_duration, 1.0))
             for w in seg.words or []:
                 ws = float(w.start)
                 we = float(w.end)