espnet.nets.scorers.length_bonus.LengthBonus

source

class espnet.nets.scorers.length_bonus.LengthBonus(n_vocab: int)

Bases: BatchScorerInterface

Length bonus in beam search.

Initialize class.

• Parameters:n_vocab (int) – The number of tokens in vocabulary for beam search

batch_score(ys: Tensor, states: List[Any], xs: Tensor) → Tuple[Tensor, List[Any]]

Score new token batch.

• Parameters:
  • ys (torch.Tensor) – torch.int64 prefix tokens (n_batch, ylen).
  • states (List *[*Any ]) – Scorer states for prefix tokens.
  • xs (torch.Tensor) – The encoder feature that generates ys (n_batch, xlen, n_feat).
• Returns: Tuple of : batchfied scores for next token with shape of (n_batch, n_vocab) and next state list for ys.
• Return type: tuple[torch.Tensor, List[Any]]

score(y, state, x)

Score new token.

• Parameters:
  • y (torch.Tensor) – 1D torch.int64 prefix tokens.
  • state – Scorer state for prefix tokens
  • x (torch.Tensor) – 2D encoder feature that generates ys.
• Returns: Tuple of : torch.float32 scores for next token (n_vocab) and None
• Return type: tuple[torch.Tensor, Any]