Upload predict.py

predict.py

@@ -0,0 +1,87 @@
+import numpy as np
+import os
+import logging
+import soundfile as sf
+import librosa
+import traceback
+
+logging.basicConfig(level=logging.DEBUG)
+logger = logging.getLogger(__name__)
+
+def extract_features(file_path):
+    """Extract audio features from a file."""
+    try:
+        logger.info(f"Starting feature extraction for: {file_path}")
+        
+        # Verify file exists
+        if not os.path.exists(file_path):
+            logger.error(f"File does not exist: {file_path}")
+            return None
+            
+        # Verify file format
+        try:
+            with sf.SoundFile(file_path) as sf_file:
+                logger.info(f"Audio file info: {sf_file.samplerate}Hz, {sf_file.channels} channels")
+        except Exception as e:
+            logger.error(f"Error reading audio file with soundfile: {str(e)}\n{traceback.format_exc()}")
+            return None
+
+        # Load audio file with error handling
+        try:
+            logger.info("Loading audio file...")
+            y, sr = librosa.load(file_path, duration=30, sr=None)
+            if len(y) == 0:
+                logger.error("Audio file is empty")
+                return None
+            logger.info(f"Successfully loaded audio: {len(y)} samples, {sr}Hz sample rate")
+        except Exception as e:
+            logger.error(f"Error loading audio: {str(e)}\n{traceback.format_exc()}")
+            return None
+
+        # Ensure minimum duration
+        duration = len(y) / sr
+        logger.info(f"Audio duration: {duration:.2f} seconds")
+        if duration < 1.0:
+            logger.error("Audio file is too short (less than 1 second)")
+            return None
+
+        features_dict = {}
+        
+        try:
+            # 1. MFCC (13 features x 2 = 26)
+            logger.info("Extracting MFCC features...")
+            mfccs = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=13)
+            features_dict['mfccs_mean'] = np.mean(mfccs, axis=1)
+            features_dict['mfccs_var'] = np.var(mfccs, axis=1)
+            logger.info(f"MFCC features shape: {mfccs.shape}")
+        except Exception as e:
+            logger.error(f"Error extracting MFCC: {str(e)}\n{traceback.format_exc()}")
+            return None
+
+        try:
+            # 2. Chroma Features
+            logger.info("Extracting chroma features...")
+            chroma = librosa.feature.chroma_stft(y=y, sr=sr)
+            features_dict['chroma'] = np.mean(chroma, axis=1)
+            logger.info(f"Chroma features shape: {chroma.shape}")
+        except Exception as e:
+            logger.error(f"Error extracting chroma features: {str(e)}\n{traceback.format_exc()}")
+            return None
+
+        # Combine all features
+        try:
+            logger.info("Combining features...")
+            features = np.concatenate([
+                features_dict['mfccs_mean'],
+                features_dict['mfccs_var'],
+                features_dict['chroma']
+            ])
+            logger.info(f"Final feature vector shape: {features.shape}")
+            return features
+        except Exception as e:
+            logger.error(f"Error combining features: {str(e)}\n{traceback.format_exc()}")
+            return None
+
+    except Exception as e:
+        logger.error(f"Unexpected error in feature extraction: {str(e)}\n{traceback.format_exc()}")
+        return None