espnet.nets.lm_interface.LMInterface

source

class espnet.nets.lm_interface.LMInterface

Bases: ScorerInterface

LM Interface for ESPnet model implementation.

static add_arguments(parser)

Add arguments to command line argument parser.

classmethod build(n_vocab: int, **kwargs)

Initialize this class with python-level args.

• Parameters:idim (int) – The number of vocabulary.
• Returns: A new instance of LMInterface.
• Return type: LMinterface

forward(x, t)

Compute LM loss value from buffer sequences.

• Parameters:
  • x (torch.Tensor) – Input ids. (batch, len)
  • t (torch.Tensor) – Target ids. (batch, len)
• Returns: Tuple of : loss to backward (scalar), negative log-likelihood of t: -log p(t) (scalar) and the number of elements in x (scalar)
• Return type: tuple[torch.Tensor, torch.Tensor, torch.Tensor]

Notes

The last two return values are used in perplexity: p(t)^{-n} = exp(-log p(t) / n)