Merge perf/diarize-threading: diarization progress via background thread

python/voice_to_notes/services/diarize.py

@@ -6,6 +6,7 @@ import os
 import subprocess
 import sys
 import tempfile
+import threading
 import time
 from dataclasses import dataclass, field
 from pathlib import Path
@@ -141,6 +142,7 @@ class DiarizeService:
         min_speakers: int | None = None,
         max_speakers: int | None = None,
         hf_token: str | None = None,
+        audio_duration_sec: float | None = None,
     ) -> DiarizationResult:
         """Run speaker diarization on an audio file.
 
@@ -184,12 +186,40 @@ class DiarizeService:
             flush=True,
         )
 
-        # Run diarization
-        try:
-            raw_result = pipeline(audio_path, **kwargs)
-        finally:
-            if temp_wav:
-                os.unlink(temp_wav)
+        # Run diarization in background thread for progress reporting
+        result_holder: list = [None]
+        error_holder: list[Exception | None] = [None]
+        done_event = threading.Event()
+
+        def _run():
+            try:
+                result_holder[0] = pipeline(audio_path, **kwargs)
+            except Exception as e:
+                error_holder[0] = e
+            finally:
+                done_event.set()
+
+        thread = threading.Thread(target=_run, daemon=True)
+        thread.start()
+
+        elapsed = 0.0
+        estimated_total = max(audio_duration_sec * 0.5, 30.0) if audio_duration_sec else 120.0
+        while not done_event.wait(timeout=2.0):
+            elapsed += 2.0
+            pct = min(20 + int((elapsed / estimated_total) * 65), 85)
+            write_message(progress_message(
+                request_id, pct, "diarizing",
+                f"Analyzing speakers ({int(elapsed)}s elapsed)..."))
+
+        thread.join()
+
+        # Clean up temp file
+        if temp_wav:
+            os.unlink(temp_wav)
+
+        if error_holder[0] is not None:
+            raise error_holder[0]
+        raw_result = result_holder[0]
 
         # pyannote 4.0+ returns DiarizeOutput; older versions return Annotation directly
         if hasattr(raw_result, "speaker_diarization"):