i used the following code to read my audio file

from scipy.io import wavfile
samplerate, data = wavfile.read("the path of my audio")

but when i tried to save values of data which i get from this code, i found that the length of data variable was 1323000, and it is impossible to represent audio file in (csv)dataset as 1323000 columns for each audio file

so how do I represent my audio file to save it in csv file,i would be grateful if any one teach me !


1 Answer 1


we can use Audio spectrogram features to represent audio, i use this linkas a guide for me
represent audio sound in the data set


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.