feat: add local Resemblyzer speaker recognition

2026-09-11 13:49:27 +02:00
parent 43fc8aaec0
commit f86af983e8
48 changed files with 5250 additions and 273 deletions
@@ -0,0 +1,82 @@
+using MeetingAssistant.Transcription;
+
+namespace MeetingAssistant.Speakers;
+
+internal sealed record SpeakerSampleSpan(
+    string Speaker,
+    TimeSpan Start,
+    TimeSpan End,
+    TimeSpan SpeechDuration,
+    TimeSpan MaximumDuration,
+    IReadOnlyList<TranscriptionSegment> Segments)
+{
+    public static SpeakerSampleSpan? Create(
+        TranscriptionSegment segment,
+        TimeSpan maximumDuration)
+    {
+        if (maximumDuration <= TimeSpan.Zero)
+        {
+            throw new ArgumentOutOfRangeException(
+                nameof(maximumDuration),
+                maximumDuration,
+                "Speaker sample maximum duration must be greater than zero.");
+        }
+
+        var boundedEnd = Min(segment.End, segment.Start + maximumDuration);
+        return boundedEnd > segment.Start
+            ? new SpeakerSampleSpan(
+                segment.Speaker,
+                segment.Start,
+                boundedEnd,
+                boundedEnd - segment.Start,
+                maximumDuration,
+                [segment with { End = boundedEnd }])
+            : null;
+    }
+
+    public bool TryExtend(
+        TranscriptionSegment segment,
+        out SpeakerSampleSpan extended)
+    {
+        extended = this;
+        if (!string.Equals(Speaker, segment.Speaker, StringComparison.OrdinalIgnoreCase) ||
+            segment.Start >= Start + MaximumDuration)
+        {
+            return false;
+        }
+
+        var boundedEnd = Min(segment.End, Start + MaximumDuration);
+        if (boundedEnd <= segment.Start)
+        {
+            return false;
+        }
+
+        var uncoveredStart = segment.Start > End ? segment.Start : End;
+        var additionalSpeechDuration = boundedEnd > uncoveredStart
+            ? boundedEnd - uncoveredStart
+            : TimeSpan.Zero;
+        extended = this with
+        {
+            End = boundedEnd > End ? boundedEnd : End,
+            SpeechDuration = SpeechDuration + additionalSpeechDuration,
+            Segments = Segments.Append(segment with { End = boundedEnd }).ToList()
+        };
+        return true;
+    }
+
+    public TranscriptionSegment ToSegment()
+    {
+        return new TranscriptionSegment(
+            Start,
+            End,
+            Speaker,
+            string.Join(' ', Segments
+                .Select(segment => segment.Text)
+                .Where(text => !string.IsNullOrWhiteSpace(text))));
+    }
+
+    private static TimeSpan Min(TimeSpan left, TimeSpan right)
+    {
+        return left < right ? left : right;
+    }
+}