chore: atualização geral

code/fcpxml/diarize.py

@@ -37,6 +37,36 @@ def diarization_capability(token: Optional[str]) -> Tuple[bool, str]:
     return True, "Identificação de participantes disponível."
 
 
+def _load_waveform(path: str) -> Optional[dict]:
+    """Decode ``path`` ourselves into the waveform dict pyannote accepts.
+
+    pyannote 4.x decodes audio through torchcodec, which links against a
+    specific FFmpeg major version and fails outright when the installed one
+    differs (``libavutil.56.dylib`` not found) — taking diarization down on
+    an otherwise working machine. Handing it an already-decoded waveform
+    skips that path entirely and reuses the ffmpeg extraction the acoustic
+    analysis already relies on, so video containers work too.
+
+    Returns ``None`` when decoding is not possible, letting the caller fall
+    back to passing the path and whatever pyannote can do with it.
+    """
+    try:
+        import soundfile
+        import torch
+
+        from .voice_features import decodable_audio
+
+        with decodable_audio(path) as audio_path:
+            if audio_path is None:
+                return None
+            data, sample_rate = soundfile.read(audio_path, dtype="float32", always_2d=True)
+        # soundfile gives (samples, channels); pyannote wants (channels, samples)
+        return {"waveform": torch.from_numpy(data.T), "sample_rate": int(sample_rate)}
+    except Exception:
+        logger.info("could not pre-decode %s for diarization", path)
+        return None
+
+
 def diarize(
     path: str,
     token: Optional[str],
@@ -67,7 +97,7 @@ def diarize(
         n = str(num_speakers or "").strip()
         if n.isdigit() and int(n) > 0:
             kwargs["num_speakers"] = int(n)
-        result = pipe(path, **kwargs)
+        result = pipe(_load_waveform(path) or path, **kwargs)
         # pyannote.audio >= 4.0 wraps the annotation; normalize to the raw one.
         if hasattr(result, "exclusive_speaker_diarization"):
             result = result.exclusive_speaker_diarization