espnet.nets.scorer_interface.ScorerInterface

source

class espnet.nets.scorer_interface.ScorerInterface

Bases: object

Scorer interface for beam search.

The scorer performs scoring of the all tokens in vocabulary.

Examples

• Search heuristics : * espnet.nets.scorers.length_bonus.LengthBonus
• Decoder networks of the sequence-to-sequence models : * espnet.nets.pytorch_backend.nets.transformer.decoder.Decoder
  • espnet.nets.pytorch_backend.nets.rnn.decoders.Decoder
• Neural language models : * espnet.nets.pytorch_backend.lm.transformer.TransformerLM
  • espnet.nets.pytorch_backend.lm.default.DefaultRNNLM
  • espnet.nets.pytorch_backend.lm.seq_rnn.SequentialRNNLM

final_score(state: Any) → float

Score eos (optional).

• Parameters:state – Scorer state for prefix tokens
• Returns: final score
• Return type: float

init_state(x: Tensor) → Any

Get an initial state for decoding (optional).

• Parameters:x (torch.Tensor) – The encoded feature tensor

Returns: initial state

score(y: Tensor, state: Any, x: Tensor) → Tuple[Tensor, Any]

Score new token (required).

• Parameters:
  • y (torch.Tensor) – 1D torch.int64 prefix tokens.
  • state – Scorer state for prefix tokens
  • x (torch.Tensor) – The encoder feature that generates ys.
• Returns: Tuple of : scores for next token that has a shape of (n_vocab) and next state for ys
• Return type: tuple[torch.Tensor, Any]

select_state(state: Any, i: int, new_id: int | None = None) → Any

Select state with relative ids in the main beam search.

• Parameters:
  • state – Decoder state for prefix tokens
  • i (int) – Index to select a state in the main beam search
  • new_id (int) – New label index to select a state if necessary
• Returns: pruned state
• Return type: state