gnes.encoder.audio.mfcc module

class gnes.encoder.audio.mfcc.MfccEncoder(n_mfcc=13, sample_rate=16000, max_length=100, *args, **kwargs)[source]

Bases: gnes.encoder.base.BaseAudioEncoder

batch_size = 64
encode(data, *args, **kwargs)[source]
Return type:ndarray
train(*args, **kwargs)

Train the model, need to be overrided