espnet.nets.pytorch_backend.frontends.frontend.Frontend
Less than 1 minute
espnet.nets.pytorch_backend.frontends.frontend.Frontend
class espnet.nets.pytorch_backend.frontends.frontend.Frontend(idim: int, use_wpe: bool = False, wtype: str = 'blstmp', wlayers: int = 3, wunits: int = 300, wprojs: int = 320, wdropout_rate: float = 0.0, taps: int = 5, delay: int = 3, use_dnn_mask_for_wpe: bool = True, use_beamformer: bool = False, btype: str = 'blstmp', blayers: int = 3, bunits: int = 300, bprojs: int = 320, bnmask: int = 2, badim: int = 320, ref_channel: int = -1, bdropout_rate=0.0)
Bases: Module
Frontend class.
Initialize frontend.
forward(x: ComplexTensor, ilens: LongTensor | ndarray | List[int]) → Tuple[ComplexTensor, LongTensor, ComplexTensor | None]
Calculate frontend forward propagation.