gnes.encoder.audio.vggish module

class gnes.encoder.audio.vggish.VggishEncoder(model_dir: str, max_length: int = 10, *args, **kwargs)[source]

Bases: gnes.encoder.base.BaseAudioEncoder

encode(audio: List[np.ndarray], *args, **kwargs) → numpy.ndarray[source]
post_init()[source]

Declare class attributes/members that can not be serialized in standard way

train(*args, **kwargs)

Train the model, need to be overrided