cleanup: remove dead code and duplicate docs

- Remove session-ses_2f27.md (161KB raw session log)
- Remove 49 ROOT_* duplicate files across REFERENCE/
- Remove 14 duplicate files between REFERENCE/ root and history/
- Remove asr_legacy.rs (dead code, replaced by asr.rs)
- Remove src/core/worker/ (duplicate JobWorker)
- Remove src/core/layers/ (empty directory)
- Remove 4 .bak files in src/
- Remove 7 dead private methods in worker/processor.rs
- Remove backup directory from git tracking

scripts/video_comparison_statistics.py

@@ -161,7 +161,7 @@ def print_report(report):
             print(f"Resolution: {meta.get('width', 0)}x{meta.get('height', 0)}")
             print(f"Size: {meta.get('size', 0) / 1024 / 1024:.2f} MB")
 
-        print(f"\nModule Results:")
+        print("\nModule Results:")
         print(f"{'-' * 80}")
 
         for module, data in video_data["modules"].items():
@@ -178,7 +178,7 @@ def print_report(report):
         if "asrx_fixed" in video_data["modules"]:
             stats = video_data["modules"]["asrx_fixed"].get("speaker_stats", {})
             if stats:
-                print(f"\nSpeaker Statistics (ASRX Fixed):")
+                print("\nSpeaker Statistics (ASRX Fixed):")
                 for speaker, spec in stats.items():
                     print(
                         f"  {speaker}: {spec['count']} segments, {spec['duration']:.2f}s"
@@ -188,13 +188,13 @@ def print_report(report):
     print(f"\n{'=' * 80}")
     print("SUMMARY")
     print(f"{'=' * 80}")
-    print(f"\nASRX Broken (pyannote):")
+    print("\nASRX Broken (pyannote):")
     for uuid, count in report["summary"]["asrx_broken"].items():
         if uuid != "total":
             print(f"  {uuid}: {count} segments")
     print(f"  Total: {report['summary']['asrx_broken']['total']} segments")
 
-    print(f"\nASRX Fixed (SpeechBrain):")
+    print("\nASRX Fixed (SpeechBrain):")
     for uuid, count in report["summary"]["asrx_fixed"].items():
         if uuid != "total":
             print(f"  {uuid}: {count} segments")