Harden speaker identity samples

2026-05-28 12:02:44 +02:00
parent c84f8a984a
commit a72cda0c03
23 changed files with 1251 additions and 123 deletions
@@ -103,10 +103,30 @@
      "MaxMatchCandidates": 100,
      "MatchIdentityActiveAge": "365.00:00:00",
      "MaxSnippetsPerSpeaker": 3,
+      "MinimumSampleSpeechDuration": "00:00:30",
+      "MaximumSampleSegmentGap": "00:00:01",
      "SilenceBetweenSnippetsSeconds": 1,
      "LiveSampleBufferDuration": "00:10:00",
      "MergeRecentIdentityAge": "14.00:00:00",
-      "MatchTimeout": "00:03:00"
+      "MatchTimeout": "00:03:00",
+      "PyannoteValidation": {
+        "Enabled": false,
+        "MinimumSingleSpeakerCoverage": 0.9,
+        "MinimumMatchingKnownSnippetRatio": 0.5,
+        "Diarization": {
+          "Enabled": true,
+          "DockerCommand": "docker",
+          "BaseImage": "python:3.11-slim",
+          "Image": "meeting-assistant-pyannote:local",
+          "BuildImage": true,
+          "ModelsFolder": "%LOCALAPPDATA%\\MeetingAssistant\\Pyannote\\models",
+          "Model": "pyannote/speaker-diarization-3.1",
+          "AnnotationSource": "SpeakerDiarization",
+          "AlignmentMode": "PyannoteTurns",
+          "TokenEnv": "HF_TOKEN",
+          "CommandTimeout": "00:30:00"
+        }
+      }
    },
    "Automation": {
      "RulesPath": "C:\\Manuel\\meeting-assistant\\meeting-rules.local.yaml"