espnet2.asr_transducer.decoder.stateless_decoder.StatelessDecoder

source

class espnet2.asr_transducer.decoder.stateless_decoder.StatelessDecoder(vocab_size: int, embed_size: int = 256, embed_dropout_rate: float = 0.0, embed_pad: int = 0)

Bases: AbsDecoder

Stateless Transducer decoder module.

• Parameters:
  • vocab_size – Output size.
  • embed_size – Embedding size.
  • embed_dropout_rate – Dropout rate for embedding layer.
  • embed_pad – Embed/Blank symbol ID.

Construct a StatelessDecoder object.

batch_score(hyps: List[Hypothesis]) → Tuple[Tensor, None]

One-step forward hypotheses.

• Parameters:hyps – Hypotheses.
• Returns: Decoder output sequences. (B, D_dec) states: Decoder hidden states. None
• Return type: out

create_batch_states(new_states: List[Tensor | None]) → None

Create decoder hidden states.

• Parameters:new_states – Decoder hidden states. [N x None]
• Returns: Decoder hidden states. None
• Return type: states

forward(labels: Tensor, states: Any | None = None) → Tensor

Encode source label sequences.

• Parameters:
  • labels – Label ID sequences. (B, L)
  • states – Decoder hidden states. None
• Returns: Decoder output sequences. (B, U, D_emb)
• Return type: embed

init_state(batch_size: int) → None

Initialize decoder states.

• Parameters:batch_size – Batch size.
• Returns: Initial decoder hidden states. None

score(label_sequence: List[int], states: Any | None = None) → Tuple[Tensor, None]

One-step forward hypothesis.

• Parameters:
  • label_sequence – Current label sequence.
  • states – Decoder hidden states. None
• Returns: Decoder output sequence. (1, D_emb) state: Decoder hidden states. None

select_state(states: Tensor | None, idx: int) → None

Get specified ID state from decoder hidden states.

• Parameters:
  • states – Decoder hidden states. None
  • idx – State ID to extract.
• Returns: Decoder hidden state for given ID. None

set_device(device: device) → None

Set GPU device to use.

• Parameters:device – Device ID.