paddlespeech.s2t.decoders.scorers.length_bonus module

Length bonus module.

class paddlespeech.s2t.decoders.scorers.length_bonus.LengthBonus(n_vocab: int)

Bases: BatchScorerInterface

Length bonus in beam search.

Methods

batch_init_state(x)	Get an initial state for decoding (optional).
batch_score(ys, states, xs)	Score new token batch.
final_score(state)	Score eos (optional).
init_state(x)	Get an initial state for decoding (optional).
score(y, state, x)	Score new token.
select_state(state, i[, new_id])	Select state with relative ids in the main beam search.

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

Score new token batch.

Args:

ys (paddle.Tensor): paddle.int64 prefix tokens (n_batch, ylen). states (List[Any]): Scorer states for prefix tokens. xs (paddle.Tensor):

The encoder feature that generates ys (n_batch, xlen, n_feat).

Returns:

tuple[paddle.Tensor, List[Any]]: Tuple of

batchfied scores for next token with shape of (n_batch, n_vocab) and next state list for ys.

score(y, state, x)

Score new token.

Args:

y (paddle.Tensor): 1D paddle.int64 prefix tokens. state: Scorer state for prefix tokens x (paddle.Tensor): 2D encoder feature that generates ys.

Returns:

tuple[paddle.Tensor, Any]: Tuple of

paddle.float32 scores for next token (n_vocab) and None