Upload Detect.py

Detect.py

+import os
+import numpy as np
+import librosa
+import tensorflow as tf
+
+# Load the saved model
+model = tf.keras.models.load_model('model.h5')
+
+# Define a function to extract features from the audio file
+def extract_features(audio_path):
+    # Load the audio file
+    y, sr = librosa.load(audio_path, sr=22050, duration=3)
+    # Extract features using Mel-frequency cepstral coefficients (MFCC)
+    mfcc = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=20)
+    # Compute the mean of each feature dimension
+    mfcc_mean = np.mean(mfcc, axis=1)
+    # Compute the first and second derivatives of the MFCC features
+    mfcc_delta = librosa.feature.delta(mfcc)
+    mfcc_delta2 = librosa.feature.delta(mfcc, order=2)
+    # Compute the mean of each derivative feature dimension
+    mfcc_delta_mean = np.mean(mfcc_delta, axis=1)
+    mfcc_delta2_mean = np.mean(mfcc_delta2, axis=1)
+    # Concatenate the feature vectors
+    features = np.concatenate((mfcc_mean, mfcc_delta_mean, mfcc_delta2_mean))
+    return features
+
+# Define a function to predict the mood from the audio file
+def predict_mood(audio_path):
+    # Extract features from the audio file
+    features = extract_features(audio_path)
+    # Reshape the features to match the input shape of the model
+    features = features.reshape(1, -1)
+    # Make the prediction
+    predictions = model.predict(features)
+    # Convert the prediction to an emotion label
+    emotion_labels = ['angry', 'calm', 'disgust', 'fearful', 'happy', 'neutral', 'sad']
+    predicted_label = emotion_labels[np.argmax(predictions)]
+    return predicted_label
+
+# Test the function on an example audio file
+audio_file = 'audio.wav'
+predicted_mood = predict_mood(audio_file)
+print('Predicted mood:', predicted_mood)