Merge pull request #722 from dfengpo/master

修复C# CalculateProb方法计算句子EndOffset的bug

Author: snakers4

examples/csharp/Program.cs

@@ -21,7 +21,7 @@ public static void Main(string[] args)
                 MIN_SPEECH_DURATION_MS, MAX_SPEECH_DURATION_SECONDS, MIN_SILENCE_DURATION_MS, SPEECH_PAD_MS);
             List<SileroSpeechSegment> speechTimeList = vadDetector.GetSpeechSegmentList(new FileInfo(EXAMPLE_WAV_FILE));
             //Console.WriteLine(speechTimeList.ToJson());
-            StringBuilder sb = new StringBuilder();
+            StringBuilder sb = new();
             foreach (var speechSegment in speechTimeList)
             {
                 sb.Append($"start second: {speechSegment.StartSecond}, end second: {speechSegment.EndSecond}\n");

examples/csharp/SileroVadDetector.cs

@@ -53,28 +53,26 @@ public List<SileroSpeechSegment> GetSpeechSegmentList(FileInfo wavFile)
     {
         Reset();
 
-        using (var audioFile = new AudioFileReader(wavFile.FullName))
-        {
-            List<float> speechProbList = new List<float>();
-            this._audioLengthSamples = (int)(audioFile.Length / 2);
-            float[] buffer = new float[this._windowSizeSample];
-
-            while (audioFile.Read(buffer, 0, buffer.Length) > 0)
-            {
-                float speechProb = _model.Call(new[] { buffer }, _samplingRate)[0];
-                speechProbList.Add(speechProb);
-            }
+        using var audioFile = new AudioFileReader(wavFile.FullName);
+        List<float> speechProbList = [];
+        this._audioLengthSamples = (int)(audioFile.Length / 2);
+        float[] buffer = new float[this._windowSizeSample];
 
-            return CalculateProb(speechProbList);
+        while (audioFile.Read(buffer, 0, buffer.Length) > 0)
+        {
+            float speechProb = _model.Call([buffer], _samplingRate)[0];
+            speechProbList.Add(speechProb);
         }
+
+        return CalculateProb(speechProbList);
     }
 
     private List<SileroSpeechSegment> CalculateProb(List<float> speechProbList)
     {
-        List<SileroSpeechSegment> result = new List<SileroSpeechSegment>();
+        List<SileroSpeechSegment> result = [];
         bool triggered = false;
         int tempEnd = 0, prevEnd = 0, nextStart = 0;
-        SileroSpeechSegment segment = new SileroSpeechSegment();
+        SileroSpeechSegment segment = new();
 
         for (int i = 0; i < speechProbList.Count; i++)
         {
@@ -164,7 +162,8 @@ private List<SileroSpeechSegment> CalculateProb(List<float> speechProbList)
 
         if (segment.StartOffset != null && (_audioLengthSamples - segment.StartOffset) > _minSpeechSamples)
         {
-            segment.EndOffset = _audioLengthSamples;
+            //segment.EndOffset = _audioLengthSamples;
+            segment.EndOffset = speechProbList.Count * _windowSizeSample;
             result.Add(segment);
         }
 
@@ -182,7 +181,7 @@ private List<SileroSpeechSegment> CalculateProb(List<float> speechProbList)
                 int silenceDuration = nextItem.StartOffset.Value - item.EndOffset.Value;
                 if (silenceDuration < 2 * _speechPadSamples)
                 {
-                    item.EndOffset = item.EndOffset + (silenceDuration / 2);
+                    item.EndOffset += (silenceDuration / 2);
                     nextItem.StartOffset = Math.Max(0, nextItem.StartOffset.Value - (silenceDuration / 2));
                 }
                 else
@@ -200,9 +199,9 @@ private List<SileroSpeechSegment> CalculateProb(List<float> speechProbList)
         return MergeListAndCalculateSecond(result, _samplingRate);
     }
 
-    private List<SileroSpeechSegment> MergeListAndCalculateSecond(List<SileroSpeechSegment> original, int samplingRate)
+    private static List<SileroSpeechSegment> MergeListAndCalculateSecond(List<SileroSpeechSegment> original, int samplingRate)
     {
-        List<SileroSpeechSegment> result = new List<SileroSpeechSegment>();
+        List<SileroSpeechSegment> result = [];
         if (original == null || original.Count == 0)
         {
             return result;
@@ -216,7 +215,10 @@ private List<SileroSpeechSegment> MergeListAndCalculateSecond(List<SileroSpeechS
             for (int i = 1; i < original.Count; i++)
             {
                 SileroSpeechSegment segment = original[i];
+                if (i == 235)
+                {
 
+                }
                 if (segment.StartOffset > right)
                 {
                     result.Add(new SileroSpeechSegment(left, right,
@@ -242,7 +244,7 @@ private List<SileroSpeechSegment> MergeListAndCalculateSecond(List<SileroSpeechS
         return result;
     }
 
-    private float CalculateSecondByOffset(int offset, int samplingRate)
+    private static float CalculateSecondByOffset(int offset, int samplingRate)
     {
         float secondValue = offset * 1.0f / samplingRate;
         return (float)Math.Floor(secondValue * 1000.0f) / 1000.0f;