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 +1,142 @@
+using MeetingAssistant.Speakers;
+using MeetingAssistant.Transcription;
+
+namespace MeetingAssistant.Tests;
+
+public sealed class SpeakerSampleSpanSelectorTests
+{
+    [Fact]
+    public void SelectBestSameSpeakerSpanCombinesLinesAndCapsTheClip()
+    {
+        var span = SpeakerSampleSpanSelector.SelectBestSameSpeakerSpan(
+            [
+                Segment(0, 4),
+                Segment(7, 13),
+                Segment(20, 70)
+            ],
+            "Guest01",
+            TimeSpan.FromSeconds(10),
+            TimeSpan.FromSeconds(60));
+
+        Assert.Equal(3, span.Count);
+        Assert.Equal(TimeSpan.Zero, span[0].Start);
+        Assert.Equal(TimeSpan.FromSeconds(60), span[^1].End);
+        Assert.Equal(TimeSpan.FromSeconds(60), SpeakerSampleSpanSelector.SpanDuration(span));
+    }
+
+    [Fact]
+    public void SelectBestSameSpeakerSpanDoesNotCountProviderPausesAsSpeakerAudio()
+    {
+        var span = SpeakerSampleSpanSelector.SelectBestSameSpeakerSpan(
+            [
+                Segment(0, 4),
+                Segment(20, 25)
+            ],
+            "Guest01",
+            TimeSpan.FromSeconds(10),
+            TimeSpan.FromSeconds(60));
+
+        Assert.Empty(span);
+    }
+
+    [Fact]
+    public void SelectBestSameSpeakerSpansReturnsDistinctMinimumLengthSamples()
+    {
+        var segments = Enumerable.Range(0, 6)
+            .Select(index => new TranscriptionSegment(
+                TimeSpan.FromSeconds(index * 10),
+                TimeSpan.FromSeconds((index + 1) * 10),
+                "Guest01",
+                $"segment {index} has enough words"))
+            .ToList();
+
+        var spans = SpeakerSampleSpanSelector.SelectBestSameSpeakerSpans(
+            segments,
+            "Guest01",
+            TimeSpan.FromSeconds(10),
+            TimeSpan.FromSeconds(60),
+            maxSpans: 5);
+
+        Assert.Equal(5, spans.Count);
+        Assert.All(spans, span => Assert.True(SpeakerSampleSpanSelector.SpanDuration(span) >= TimeSpan.FromSeconds(10)));
+        Assert.All(
+            spans.Zip(spans.Skip(1)),
+            pair => Assert.True(pair.First[^1].End <= pair.Second[0].Start));
+    }
+
+    [Fact]
+    public void SelectBestSameSpeakerSpansSkipsSegmentsThatOverlapACompletedSample()
+    {
+        var spans = SpeakerSampleSpanSelector.SelectBestSameSpeakerSpans(
+            [
+                Segment(0, 10),
+                Segment(9, 19),
+                Segment(20, 30)
+            ],
+            "Guest01",
+            TimeSpan.FromSeconds(10),
+            TimeSpan.FromSeconds(60),
+            maxSpans: 5);
+
+        Assert.Equal(2, spans.Count);
+        Assert.Equal(TimeSpan.Zero, spans[0][0].Start);
+        Assert.Equal(TimeSpan.FromSeconds(20), spans[1][0].Start);
+    }
+
+    [Fact]
+    public void SelectBestSameSpeakerSpansCombinesConsecutiveLinesAcrossProviderPauses()
+    {
+        var spans = SpeakerSampleSpanSelector.SelectBestSameSpeakerSpans(
+            [
+                Segment(0, 4),
+                Segment(7, 13)
+            ],
+            "Guest01",
+            TimeSpan.FromSeconds(10),
+            TimeSpan.FromSeconds(60),
+            maxSpans: 5);
+
+        var span = Assert.Single(spans);
+        Assert.Equal(TimeSpan.Zero, span[0].Start);
+        Assert.Equal(TimeSpan.FromSeconds(13), span[^1].End);
+    }
+
+    [Fact]
+    public void SelectBestSameSpeakerSpansDoesNotCountProviderPausesAsSpeakerAudio()
+    {
+        var spans = SpeakerSampleSpanSelector.SelectBestSameSpeakerSpans(
+            [
+                Segment(0, 4),
+                Segment(20, 25)
+            ],
+            "Guest01",
+            TimeSpan.FromSeconds(10),
+            TimeSpan.FromSeconds(60),
+            maxSpans: 5);
+
+        Assert.Empty(spans);
+    }
+
+    [Fact]
+    public void SelectBestSameSpeakerSpansCapsFinalizedSamplesAtConfiguredMaximumDuration()
+    {
+        var spans = SpeakerSampleSpanSelector.SelectBestSameSpeakerSpans(
+            [Segment(0, 70)],
+            "Guest01",
+            TimeSpan.FromSeconds(10),
+            TimeSpan.FromSeconds(60),
+            maxSpans: 5);
+
+        var span = Assert.Single(spans);
+        Assert.Equal(TimeSpan.FromSeconds(60), SpeakerSampleSpanSelector.SpanDuration(span));
+    }
+
+    private static TranscriptionSegment Segment(double start, double end)
+    {
+        return new TranscriptionSegment(
+            TimeSpan.FromSeconds(start),
+            TimeSpan.FromSeconds(end),
+            "Guest01",
+            "enough words for this segment");
+    }
+}