espnet.nets.pytorch_backend.frontends.dnn_beamformer.AttentionReference
Less than 1 minute
espnet.nets.pytorch_backend.frontends.dnn_beamformer.AttentionReference
class espnet.nets.pytorch_backend.frontends.dnn_beamformer.AttentionReference(bidim, att_dim)
Bases: Module
Initializes internal Module state, shared by both nn.Module and ScriptModule.
forward(psd_in: ComplexTensor, ilens: LongTensor, scaling: float = 2.0) → Tuple[Tensor, LongTensor]
The forward function
- Parameters:
- psd_in (ComplexTensor) – (B, F, C, C)
- ilens (torch.Tensor) – (B,)
- scaling (float)
- Returns: (B, C) ilens (torch.Tensor): (B,)
- Return type: u (torch.Tensor)