def section_by_section_analysis(model, audio_file, to_flatten):
class_labels = ["Neutral", "Angry", "Happy", "Sad"]
entireAudio = AudioSegment.from_wav(audio_file)
chunkSize = 2000
numChunks = len(entireAudio) / chunkSize
temporaryFileName = 'tempFile.wav'
print(len(entireAudio))
print(numChunks)
previousEndTime = 0
for endTime in range(chunkSize, len(entireAudio) + chunkSize, chunkSize):
if (endTime > len(entireAudio)):
lastBit = (len(entireAudio) - previousEndTime) * -1
newAudio = entireAudio[lastBit:]
else:
newAudio = entireAudio[previousEndTime:endTime]
newAudio.export(
temporaryFileName,
format="wav") #Exports to a wav file in the current path.
predicted_value = model.predict_one(
get_feature_vector_from_mfcc(temporaryFileName,
flatten=to_flatten))
print('section:', previousEndTime, '-', endTime,
'(ms). predicted value:', predicted_value, '[',
class_labels[predicted_value], ']')
os.remove(temporaryFileName)
previousEndTime = endTime
def ml_example():
to_flatten = True
x_train, x_test, y_train, y_test, _ = extract_data(flatten=to_flatten)
model = NN()
print('Starting', model.name)
model.train(x_train, y_train)
model.evaluate(x_test, y_test)
filename = '../dataset/Sad/09b03Ta.wav'
print('prediction', model.predict_one(
get_feature_vector_from_mfcc(filename, flatten=to_flatten)),
'Actual 3')
def ml_example(url, sourceName):
print("URL is: ", url)
print("Source Name is: ", sourceName)
filename = sourceName
urllib.request.urlretrieve(url, filename)
print('file downloaded')
to_flatten = True
x_train, x_test, y_train, y_test, _ = extract_data(flatten=to_flatten)
model = NN()
print('Starting', model.name)
model.train(x_train, y_train)
model.evaluate(x_test, y_test)
# filename = testingFileName + '.wav'
# 0 => Neutral
# Neutral File 1
# filename = './dataset/Neutral/03a02Nc.wav'
# Neutral File 2
# filename = './dataset/Neutral/11b03Nb.wav'
# 1 => Angry
# Angry File 1
# filename = './dataset/Angry/03a04Wc.wav'
# Angry File 2
# filename = './dataset/Angry/10a04Wa.wav'
# 2 => Happy
# Happy File 1
# filename = './dataset/Happy/03a05Fc.wav'
# Happy File 2
# filename = './dataset/Happy/15a07Fb.wav'
# 3 => Sad
# Sad File 1
# filename = './dataset/Sad/09b03Ta.wav'
# Sad File 2
# filename = './dataset/Sad/16a05Tb.wav'
# print('prediction', model.predict_one(
# get_feature_vector_from_mfcc(filename, flatten=to_flatten)),
# 'Actual 1')
# return model.predict_one(get_feature_vector_from_mfcc(filename, flatten=to_flatten))
emotions = model.predict_one(
get_feature_vector_from_mfcc(filename, flatten=to_flatten))
print("Emotions are: ", emotions)
finalEmotion = 0
for emotion in emotions:
finalEmotion = emotion
finalEmotion = finalEmotion.item()
if finalEmotion == 0:
finalEmotion = random.choice(numbers)
print("Final Emotion is: ", finalEmotion)
return finalEmotion
def lstm_example():
to_flatten = False
x_train, x_test, y_train, y_test, num_labels = extract_data(
flatten=to_flatten)
y_train = np_utils.to_categorical(y_train)
y_test_train = np_utils.to_categorical(y_test)
print('Starting LSTM')
model = LSTM(input_shape=x_train[0].shape, num_classes=num_labels)
# model.train(x_train, y_train, x_test, y_test_train, n_epochs=50)
# model.evaluate(x_test, y_test)
filename = 'dataset/Sad/09b03Ta.wav'
print(
'prediction',
model.predict_one(
get_feature_vector_from_mfcc(filename, flatten=to_flatten)),
'Actual 3')
def lstm_saved_model():
to_flatten = False
x_train, x_test, y_train, y_test, num_labels = extract_data(
flatten=to_flatten)
y_train = np_utils.to_categorical(y_train)
y_test_train = np_utils.to_categorical(y_test)
print('Starting LSTM')
model = LSTM(input_shape=x_train[0].shape,
num_classes=num_labels, save_path="./lstm.h5")
print("Loading")
model.restore_model()
# filename = '../dataset/03a01Wa.wav'
filename = '../dataset/sad.wav'
print("\nPredicted: {}\nActual: {}".format(
get_class_name(
model.predict_one(get_feature_vector_from_mfcc(filename, flatten=to_flatten))),
get_class_name(3)))
def ml_example():
to_flatten = True
x_train, x_test, y_train, y_test, _ = extract_data(flatten=to_flatten)
model = NN()
print('Starting', model.name)
model.train(x_train, y_train)
model.evaluate(x_test, y_test)
filename = '../dataset/Sad/09b03Ta.wav'
i = model.predict_one(
get_feature_vector_from_mfcc(filename, flatten=to_flatten))
if i == 0:
print("Prediction: Angry")
elif i == 1:
print("Prediction: Happy")
elif i == 2:
print("Prediction: Neutral")
else:
print("Prediction: Sad")
def cnn_example():
to_flatten = False
x_train, x_test, y_train, y_test, num_labels = extract_data(
flatten=to_flatten)
y_train = np_utils.to_categorical(y_train)
y_test_train = np_utils.to_categorical(y_test)
in_shape = x_train[0].shape
x_train = x_train.reshape(x_train.shape[0], in_shape[0], in_shape[1], 1)
x_test = x_test.reshape(x_test.shape[0], in_shape[0], in_shape[1], 1)
model = CNN(input_shape=x_train[0].shape,
num_classes=num_labels)
model.train(x_train, y_train, x_test, y_test_train)
model.evaluate(x_test, y_test)
filename = '../dataset/Sad/09b03Ta.wav'
print('prediction', model.predict_one(
get_feature_vector_from_mfcc(filename, flatten=to_flatten)),
'Actual 3')
print('CNN Done')
def lstm_example():
to_flatten = False
x_train, x_test, y_train, y_test, num_labels = extract_data(
flatten=to_flatten)
y_train = np_utils.to_categorical(y_train)
y_test_train = np_utils.to_categorical(y_test)
print('Starting LSTM')
model = LSTM(input_shape=x_train[0].shape, num_classes=num_labels)
print('Model Object Created, Going to train Model')
model.train(x_train, y_train, x_test, y_test_train, n_epochs=50)
print('Model Object trained, Going to evaluate Model')
model.evaluate(x_test, y_test)
print('Model Object Evaludated, Going to import testing audio')
filename = './dataset/Sad/09b03Ta.wav'
print(
'prediction',
model.predict_one(
get_feature_vector_from_mfcc(filename, flatten=to_flatten)),
'Actual 3')
print('Finishing LSTM')
def lstm_example():
to_flatten = False
x_train, x_test, y_train, y_test, num_labels = extract_data(
flatten=to_flatten)
y_train = np_utils.to_categorical(y_train)
y_test_train = np_utils.to_categorical(y_test)
print('Starting LSTM')
model = LSTM(input_shape=x_train[0].shape,
num_classes=num_labels, save_path="./lstm.h5")
print("Training")
model.train(x_train, y_train, x_test, y_test_train, n_epochs=10)
print("Evaluating")
model.evaluate(x_test, y_test)
model.save_model()
filename = '../dataset/Sad/09b03Ta.wav'
# filename = './laugh.wav'
print("\nPredicted: {}\nActual: {}".format(
get_class_name(
model.predict_one(
get_feature_vector_from_mfcc(filename, flatten=to_flatten))),
get_class_name(2)))
def get_feature_vector(file_path, flatten):
return get_feature_vector_from_mfcc(file_path, flatten, mfcc_len=39)
def get_feature_vector(flatten, file_path="dataset"):
return get_feature_vector_from_mfcc(file_path, flatten, mfcc_len=39)
