espnet.nets.pytorch_backend.e2e_asr_maskctc.E2E

source

class espnet.nets.pytorch_backend.e2e_asr_maskctc.E2E(idim, odim, args, ignore_id=-1)

Bases: E2E

E2E module.

• Parameters:
  • idim (int) – dimension of inputs
  • odim (int) – dimension of outputs
  • args (Namespace) – argument Namespace containing options

Construct an E2E object.

• Parameters:
  • idim (int) – dimension of inputs
  • odim (int) – dimension of outputs
  • args (Namespace) – argument Namespace containing options

static add_arguments(parser)

Add arguments.

static add_maskctc_arguments(parser)

Add arguments for maskctc model.

forward(xs_pad, ilens, ys_pad)

E2E forward.

• Parameters:
  • xs_pad (torch.Tensor) – batch of padded source sequences (B, Tmax, idim)
  • ilens (torch.Tensor) – batch of lengths of source sequences (B)
  • ys_pad (torch.Tensor) – batch of padded target sequences (B, Lmax)
• Returns: ctc loss value
• Return type: torch.Tensor
• Returns: attention loss value
• Return type: torch.Tensor
• Returns: accuracy in attention decoder
• Return type: float

recognize(x, recog_args, char_list=None, rnnlm=None)

Recognize input speech.

• Parameters:
  • x (ndnarray) – input acoustic feature (B, T, D) or (T, D)
  • recog_args (Namespace) – argment Namespace contraining options
  • char_list (list) – list of characters
  • rnnlm (torch.nn.Module) – language model module
• Returns: decoding result
• Return type: list