espnet2.asr.ctc.CTC

source

class espnet2.asr.ctc.CTC(odim: int, encoder_output_size: int, dropout_rate: float = 0.0, ctc_type: str = 'builtin', reduce: bool = True, ignore_nan_grad: bool | None = None, zero_infinity: bool = True, brctc_risk_strategy: str = 'exp', brctc_group_strategy: str = 'end', brctc_risk_factor: float = 0.0)

Bases: Module

CTC module.

• Parameters:
  • odim – dimension of outputs
  • encoder_output_size – number of encoder projection units
  • dropout_rate – dropout rate (0.0 ~ 1.0)
  • ctc_type – builtin or gtnctc
  • reduce – reduce the CTC loss into a scalar
  • ignore_nan_grad – Same as zero_infinity (keeping for backward compatiblity)
  • zero_infinity – Whether to zero infinite losses and the associated gradients.

Initialize internal Module state, shared by both nn.Module and ScriptModule.

argmax(hs_pad)

argmax of frame activations

• Parameters:hs_pad (torch.Tensor) – 3d tensor (B, Tmax, eprojs)
• Returns: argmax applied 2d tensor (B, Tmax)
• Return type: torch.Tensor

forced_align(hs_pad, hlens, ys_pad, ys_lens, blank_idx=0)

Force alignment between input and target sequences (Viterbi path).

• Parameters:
  • hs_pad – batch of padded hidden state sequences (B, Tmax, D)
  • hlens – batch of lengths of hidden state sequences (B)
  • ys_pad – batch of padded character id sequence tensor (B, Lmax)
  • ys_lens – batch of lengths of character sequence (B)
  • blank_idx – index of blank symbol
  • Note – B must be 1.
• Returns: Tuple(tensor, tensor): : - Label for each time step in the alignment path computed <br/> using forced alignment.
  • Log probability scores of the labels for each time step.
• Return type: alignments

forward(hs_pad, hlens, ys_pad, ys_lens)

Calculate CTC loss.

• Parameters:
  • hs_pad – batch of padded hidden state sequences (B, Tmax, D)
  • hlens – batch of lengths of hidden state sequences (B)
  • ys_pad – batch of padded character id sequence tensor (B, Lmax)
  • ys_lens – batch of lengths of character sequence (B)

log_softmax(hs_pad)

log_softmax of frame activations

• Parameters:hs_pad (Tensor) – 3d tensor (B, Tmax, eprojs)
• Returns: log softmax applied 3d tensor (B, Tmax, odim)
• Return type: torch.Tensor

loss_fn(th_pred, th_target, th_ilen, th_olen) → Tensor

softmax(hs_pad)

softmax of frame activations

• Parameters:hs_pad (Tensor) – 3d tensor (B, Tmax, eprojs)
• Returns: softmax applied 3d tensor (B, Tmax, odim)
• Return type: torch.Tensor