Method forward

funasr/frontends/wav_frontend.py:149–196

Forward pass for training. Args: input: Input audio/text data. input_lengths: Lengths of input. **kwargs: Additional keyword arguments.

(
        self,
        input: torch.Tensor,
        input_lengths,
        **kwargs,
    )

        return self.n_mels * self.lfr_m

    def forward(
        self,
        input: torch.Tensor,
        input_lengths,
        **kwargs,
    ) -> Tuple[torch.Tensor, torch.Tensor]:
        """Forward pass for training.
        
            Args:
                input: Input audio/text data.
                input_lengths: Lengths of input.
                **kwargs: Additional keyword arguments.
            """
        batch_size = input.size(0)
        feats = []
        feats_lens = []
        for i in range(batch_size):
            waveform_length = input_lengths[i]
            waveform = input[i][:waveform_length]
            if self.upsacle_samples:
                waveform = waveform * (1 << 15)
            waveform = waveform.unsqueeze(0)
            mat = kaldi.fbank(
                waveform,
                num_mel_bins=self.n_mels,
                frame_length=min(self.frame_length,waveform_length/self.fs*1000),
                frame_shift=self.frame_shift,
                dither=self.dither,
                energy_floor=0.0,
                window_type=self.window,
                sample_frequency=self.fs,
                snip_edges=self.snip_edges,
            )

            if self.lfr_m != 1 or self.lfr_n != 1:
                mat = apply_lfr(mat, self.lfr_m, self.lfr_n)
            if self.cmvn is not None:
                mat = apply_cmvn(mat, self.cmvn)
            feat_length = mat.size(0)
            feats.append(mat)
            feats_lens.append(feat_length)

        feats_lens = torch.as_tensor(feats_lens)
        if batch_size == 1:
            feats_pad = feats[0][None, :, :]
        else:
            feats_pad = pad_sequence(feats, batch_first=True, padding_value=0.0)
        return feats_pad, feats_lens

    def forward_fbank(
        self, input: torch.Tensor, input_lengths: torch.Tensor