espnet.nets.pytorch_backend.lm.default.RNNLM

source

class espnet.nets.pytorch_backend.lm.default.RNNLM(n_vocab, n_layers, n_units, n_embed=None, typ='lstm', dropout_rate=0.5, emb_dropout_rate=0.0, tie_weights=False)

Bases: Module

A pytorch RNNLM.

Initialize class.

• Parameters:
  • n_vocab (int) – The size of the vocabulary
  • n_layers (int) – The number of layers to create
  • n_units (int) – The number of units per layer
  • typ (str) – The RNN type

forward(state, x)

Forward neural networks.

zero_state(batchsize)

Initialize state.