Method encode

funasr/models/scama/model.py:277–304

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]:
        """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
        encoder_out, encoder_out_lens, _ = self.encoder(speech, speech_lengths)
        if isinstance(encoder_out, tuple):
            encoder_out = encoder_out[0]

        return encoder_out, encoder_out_lens

    def encode_chunk(
        self,