Method encode

funasr/models/transformer/model.py:288–325

Frontend + Encoder. Note that this method is used by asr_inference.py Args: speech: (Batch, Length, ...) speech_lengths: (Batch, ) ind: int

(
        self,
        speech: torch.Tensor,
        speech_lengths: torch.Tensor,
        **kwargs,
    )

        return loss, stats, weight

    def encode(
        self,
        speech: torch.Tensor,
        speech_lengths: torch.Tensor,
        **kwargs,
    ) -> Tuple[torch.Tensor, torch.Tensor]:
        """Frontend + Encoder. Note that this method is used by asr_inference.py
        Args:
                speech: (Batch, Length, ...)
                speech_lengths: (Batch, )
                ind: int
        """
        with autocast(False):

            # Data augmentation
            if self.specaug is not None and self.training:
                speech, speech_lengths = self.specaug(speech, speech_lengths)

            # Normalization for feature: e.g. Global-CMVN, Utterance-CMVN
            if self.normalize is not None:
                speech, speech_lengths = self.normalize(speech, speech_lengths)

        # Forward encoder
        # feats: (Batch, Length, Dim)
        # -> encoder_out: (Batch, Length2, Dim2)
        if self.encoder.interctc_use_conditioning:
            encoder_out, encoder_out_lens, _ = self.encoder(speech, speech_lengths, ctc=self.ctc)
        else:
            encoder_out, encoder_out_lens, _ = self.encoder(speech, speech_lengths)
        intermediate_outs = None
        if isinstance(encoder_out, tuple):
            intermediate_outs = encoder_out[1]
            encoder_out = encoder_out[0]

        if intermediate_outs is not None:
            return (encoder_out, intermediate_outs), encoder_out_lens

        return encoder_out, encoder_out_lens

    def _calc_att_loss(
        self,