The sample data is wav files from Kaggle: Emotional Speech database for classification problem
2018r...@mnit.ac.in's profile photo
2018r...@mnit.ac.in
unread,
12:00 AM (19 hours ago)
to librosa
I am using the following code snippet, want to rcv the font size of the axes also the wav file length is 2 seconds long, but why is it plotting only for 1.5 seconds plz guide.
import matplotlib.pyplot as plt
import librosa
import librosa.display
import glob
path=glob.glob('E:/Python_On_All_Dataset/Four emotion_for plot/*.wav')
fig, ax = plt.subplots(nrows=7, ncols=3, sharex=True)
plt.rcParams['font.size'] = '1'
for i in range(7) :
y, sr = librosa.load(path[i], sr=16000)
librosa.display.waveplot(y, sr, ax=ax[i, 0]) # put wave in row i, column 0
mfcc=librosa.feature.mfcc(y)
librosa.display.specshow(mfcc, x_axis='time', ax=ax[i, 1],cmap='viridis') # mfcc in row i, column 1
S = librosa.feature.melspectrogram(y, sr)
librosa.display.specshow(librosa.power_to_db(S), x_axis='time', y_axis='log', ax=ax[i, 2],cmap='viridis') # spectrogram in row i, column 2