use pre-built model to predict audio file
i am using this code to build a model that recognizes emotions in speech, but i can't figure out how to use it after loading it in a new python file. this is what i have but the results are always the same no matter what sound file i use.
model_audio = tf.keras.models.load_model(audio_emotion_classifier_tess.h5)
path = YAF_back_angry.wav
def extract_features(path):
data, sample_rate = librosa.load(path, duration=2, offset=0.6, sr=8025)
# ZCR
result = np.array([])
zcr = np.mean(librosa.feature.zero_crossing_rate(y=data).T, axis=0)
result=np.hstack((result, zcr)) # stacking horizontally
# Chroma_stft
stft = np.abs(librosa.stft(data))
chroma_stft = np.mean(librosa.feature.chroma_stft(S=stft, sr=sample_rate).T, axis=0)
result = np.hstack((result, chroma_stft)) # stacking horizontally
# MFCC
mfcc = np.mean(librosa.feature.mfcc(y=data, sr=sample_rate).T, axis=0)
result = np.hstack((result, mfcc)) # stacking horizontally
# Root Mean Square Value
rms = np.mean(librosa.feature.rms(y=data).T, axis=0)
result = np.hstack((result, rms)) # stacking horizontally
# MelSpectogram
mel = np.mean(librosa.feature.melspectrogram(y=data, sr=sample_rate).T, axis=0)
result = np.hstack((result, mel)) # stacking horizontally
return result
X = extract_features(path)
X = X.reshape(1, -1)
x_test = scaler.fit_transform(X)
predict_audio=model_audio.predict(x_test)
print(predict_audio)
Topic tensorflow deep-learning scikit-learn python
Category Data Science