fix: support videos with no audio or no faces

1. trace_done now checks for 'no_faces' status in face_traced.json
   - Videos with no detected faces now complete correctly
   - Previously stuck because trace_count=0 returned false

2. ASRX fallback to ASR segments includes start_frame/end_frame
   - Added _convert_asr_segments_to_asrx helper function
   - TKG can now process fallback segments correctly

This allows processing of:
- Videos with no audio track (ASR: no_audio_track)
- Videos with no faces (face_traced.json: no_faces)

scripts/asrx_processor.py

@@ -110,6 +110,39 @@ def _shared_audio_setup(video_path):
     return tmp_dir, video_path
 
 
+def _convert_asr_segments_to_asrx(asr_segments, output_path):
+    """Convert ASR segments to ASRX format with frame information"""
+    fps = 30.0
+    base_name = os.path.basename(output_path)
+    uuid_part = base_name.split(".")[0]
+    probe_path = os.path.join(os.path.dirname(output_path),
+                              f"{uuid_part}.probe.json")
+    if os.path.exists(probe_path):
+        try:
+            with open(probe_path) as pf:
+                probe_data = json.load(pf)
+                if "fps" in probe_data:
+                    fps = float(probe_data["fps"])
+        except Exception:
+            pass
+
+    segments = []
+    for s in asr_segments:
+        start_time = s.get("start", s.get("start_time", 0))
+        end_time = s.get("end", s.get("end_time", 0))
+        start_frame = int(start_time * fps)
+        end_frame = int(end_time * fps)
+        segments.append({
+            "start_time": start_time,
+            "end_time": end_time,
+            "start_frame": start_frame,
+            "end_frame": end_frame,
+            "text": s.get("text", ""),
+            "speaker_id": "SPEAKER_0",
+        })
+    return segments
+
+
 def _convert_result(result, output_path):
     """Stage 3: 將 SelfASRXFixed result 轉為 Rust-expected format"""
     fps = 30.0
@@ -231,11 +264,12 @@ def process_asrx(video_path: str, output_path: str, uuid: str = "",
                 # Fallback to ASR segments if ASRX fails but ASR has content
                 if asr_segments:
                     print(f"[ASRX] Resume error, falling back to {len(asr_segments)} ASR segments", file=sys.stderr)
+                    segments = _convert_asr_segments_to_asrx(asr_segments, output_path)
                     output_result = {
                         "status": "has_transcript",
                         "language": None,
-                        "segments": [{"start_time": s["start"], "end_time": s["end"], "text": s["text"], "speaker_id": "SPEAKER_0"} for s in asr_segments],
-                        "segment_count": len(asr_segments),
+                        "segments": segments,
+                        "segment_count": len(segments),
                         "fallback_from_asr": True,
                     }
                 else: