gnes.encoder.audio.mfcc module

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

Bases: gnes.encoder.base.BaseAudioEncoder

batch_size = 64
encode(data: List[np.array], *args, **kwargs) → numpy.ndarray[source]
train(*args, **kwargs)

Train the model, need to be overrided