espnet2.s2t.espnet_model.ESPnetS2TModel

source

class espnet2.s2t.espnet_model.ESPnetS2TModel(vocab_size: int, token_list: Tuple[str, ...] | List[str], frontend: AbsFrontend | None, specaug: AbsSpecAug | None, normalize: AbsNormalize | None, preencoder: AbsPreEncoder | None, encoder: AbsEncoder, postencoder: AbsPostEncoder | None, decoder: AbsDecoder | None, ctc: CTC, ctc_weight: float = 0.5, interctc_weight: float = 0.0, ignore_id: int = -1, lsm_weight: float = 0.0, length_normalized_loss: bool = False, report_cer: bool = True, report_wer: bool = True, sym_space: str = '<space>', sym_blank: str = '<blank>', sym_sos: str = '<sos>', sym_eos: str = '<eos>', sym_sop: str = '<sop>', sym_na: str = '<na>', extract_feats_in_collect_stats: bool = True)

Bases: AbsESPnetModel

CTC-attention hybrid Encoder-Decoder model

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

collect_feats(speech: Tensor, speech_lengths: Tensor, text: Tensor, text_lengths: Tensor, text_prev: Tensor, text_prev_lengths: Tensor, text_ctc: Tensor, text_ctc_lengths: Tensor, **kwargs) → Dict[str, Tensor]

encode(speech: Tensor, speech_lengths: Tensor) → Tuple[Tensor, Tensor]

Frontend + Encoder. Note that this method is used by s2t_inference.py

• Parameters:
  • speech – (Batch, Length, …)
  • speech_lengths – (Batch, )

forward(speech: Tensor, speech_lengths: Tensor, text: Tensor, text_lengths: Tensor, text_prev: Tensor, text_prev_lengths: Tensor, text_ctc: Tensor, text_ctc_lengths: Tensor, **kwargs) → Tuple[Tensor, Dict[str, Tensor], Tensor]

Frontend + Encoder + Decoder + Calc loss

• Parameters:
  • speech – (Batch, Length, …)
  • speech_lengths – (Batch, )
  • text – (Batch, Length)
  • text_lengths – (Batch,)
  • text_prev – (Batch, Length)
  • text_prev_lengths – (Batch,)
  • text_ctc – (Batch, Length)
  • text_ctc_lengths – (Batch,)
  • kwargs – “utt_id” is among the input.