Update app.py

app.py

@@ -4,20 +4,36 @@ import librosa
 import numpy as np
 
 # Diccionario de etiquetas
-labels = ['down', 'go', 'left', 'no', 'off', 'on', 'right', 'stop', 'up', 'yes'] 
+labels = ['down', 'go', 'left', 'no', 'off', 'on', 'right', 'stop', 'up', 'yes']
+
+def extract_features(file_name):
+    try:
+        audio, sample_rate = librosa.load(file_name, res_type='kaiser_fast') 
+        mfccs = librosa.feature.mfcc(y=audio, sr=sample_rate, n_mfcc=40)
+        mfccsscaled = np.mean(mfccs.T,axis=0)
+        
+    except Exception as e:
+        print("Error encountered while parsing file: ", file_name)
+        return None 
+     
+    return mfccsscaled
 
 def classify_audio(audio_file):
     # Carga el modelo
-    model = tf.keras.models.load_model('my_model.h5')  
+    model = tf.keras.models.load_model('my_model.h5') 
 
     # Preprocesa el audio
-    audio, sr = librosa.load(audio_file, sr=8000) 
-    mfccs = librosa.feature.mfcc(y=audio, sr=sr, n_mfcc=40)
-    mfccs_processed = np.mean(mfccs.T,axis=0) 
-    mfccs_processed = mfccs_processed.reshape(1, 40, 1) # Redimensiona a (1, 40, 1)
-
+    features = extract_features(audio_file)
+    if features is None:
+        return "Error al procesar el audio" # Manejo de error
+    
+    features = features.reshape(1, -1) # Redimensiona a (1, 40)
+    
+    # Si tu modelo necesita 3 dimensiones, redimensiona a (1, 40, 1)
+    # features = features.reshape(1, 40, 1)
+    
     # Realiza la predicción
-    prediction = model.predict(mfccs_processed)
+    prediction = model.predict(features)
     predicted_label_index = np.argmax(prediction) 
 
     # Devuelve la etiqueta predicha