In Python one would write:

file_name = 'fdsafdsafds.wav'
audio, sample_rate = librosa.load(file_name, res_type='kaiser_fast') 
mfccs = librosa.feature.mfcc(y=audio, sr=sample_rate, n_mfcc=40)

Is there such a library or the one with this functionality in other, compiled languages? in C++, Go, Rust, .NET… I haven’t found any

  • @vcmj
    link
    09 months ago

    Not an answer to the question, but in case performance is the goal, Torchaudio has it here