espnet2.legacy.nets.pytorch_backend.rnn.encoders.RNN

source

class espnet2.legacy.nets.pytorch_backend.rnn.encoders.RNN(idim, elayers, cdim, hdim, dropout, typ='blstm')

Bases: Module

RNN module.

• Parameters:
  • idim (int) – dimension of inputs
  • elayers (int) – number of encoder layers
  • cdim (int) – number of rnn units (resulted in cdim * 2 if bidirectional)
  • hdim (int) – number of final projection units
  • dropout (float) – dropout rate
  • typ (str) – The RNN type

Initialize RNN.

forward(xs_pad, ilens, prev_state=None)

Forward RNN.

• Parameters:
  • xs_pad (torch.Tensor) – batch of padded input sequences (B, Tmax, D)
  • ilens (torch.Tensor) – batch of lengths of input sequences (B)
  • prev_state (torch.Tensor) – batch of previous RNN states
• Returns: batch of hidden state sequences (B, Tmax, eprojs)
• Return type: torch.Tensor