记录三模型话轮检测实验、44点评估及延迟对比

experiments/smart-turn-v3.2/predict.py

@@ -0,0 +1,61 @@
+import argparse
+import librosa
+import sys
+import numpy as np
+
+from inference import predict_endpoint
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Smart Turn v3.2 CPU inference")
+    parser.add_argument("audio", help="Audio file to analyze")
+    parser.add_argument("--start-ms", type=int, default=0, help="Current user turn start")
+    parser.add_argument("--end-ms", type=int, help="Decision time (exclusive audio cutoff)")
+    args = parser.parse_args()
+    if args.start_ms < 0 or (args.end_ms is not None and args.end_ms <= args.start_ms):
+        parser.error("Require 0 <= start-ms < end-ms")
+    file_path = args.audio
+
+    try:
+        print(f"Loading audio file: {file_path}")
+        # Load the audio file with original sample rate
+        audio, sr = librosa.load(file_path, sr=None, mono=True)
+
+        # Slice before resampling so no audio after the decision is included.
+        start_sample = args.start_ms * sr // 1000
+        end_sample = len(audio) if args.end_ms is None else args.end_ms * sr // 1000
+        if start_sample >= len(audio) or end_sample > len(audio):
+            raise ValueError("Requested time range lies outside the audio")
+        audio = audio[start_sample:end_sample]
+
+        print(f"Loaded audio with sample rate: {sr} Hz, duration: {len(audio) / sr:.2f} seconds")
+
+        # If needed, resample to 16kHz (the model's expected sample rate)
+        if sr != 16000:
+            print(f"Resampling from {sr}Hz to 16000Hz")
+            audio = librosa.resample(audio, orig_sr=sr, target_sr=16000)
+
+        # Convert audio to float32 if not already
+        if audio.dtype != np.float32:
+            audio = audio.astype(np.float32)
+
+        # Make sure the audio is in the expected range [-1, 1]
+        if np.max(np.abs(audio)) > 1.0:
+            audio = audio / np.max(np.abs(audio))
+
+        # Call the prediction function with both audio and sample rate
+        print("Running endpoint prediction...")
+        result = predict_endpoint(audio)
+
+        # Display results
+        print("\nResults:")
+        print(f"Prediction: {'Complete' if result['prediction'] == 1 else 'Incomplete'}")
+        print(f"Probability of complete: {result['probability']:.4f}")
+
+    except Exception as e:
+        print(f"Error processing audio file: {e}")
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()