| | |
|---|
| | | |
|---|
| | | def prepare_mask(self, mask, sub_masks): |
|---|
| | | mask_3d_btd = mask[:, :, None] |
|---|
| | | # sub_masks = subsequent_mask(mask.size(-1)).type(torch.float32) |
|---|
| | | if len(mask.shape) == 2: |
|---|
| | | mask_4d_bhlt = 1 - sub_masks[:, None, None, :] |
|---|
| | | elif len(mask.shape) == 3: |
|---|
| | | mask_4d_bhlt = 1 - sub_masks[:, None, :] |
|---|
| | | mask_4d_bhlt = mask_4d_bhlt * -10000.0 |
|---|
| | | mask_4d_bhlt = (1 - sub_masks) * -10000.0 |
|---|
| | | |
|---|
| | | return mask_3d_btd, mask_4d_bhlt |
|---|
| | | |
|---|
| | |
|---|
| | | speech = speech * self._output_size ** 0.5 |
|---|
| | | mask = self.make_pad_mask(speech_lengths) |
|---|
| | | mask = self.prepare_mask(mask, sub_masks) |
|---|
| | | vad_mask = self.prepare_mask(mask, vad_mask) |
|---|
| | | if self.embed is None: |
|---|
| | | xs_pad = speech |
|---|
| | | else: |
|---|
| | |
|---|
| | | # encoder_outs = self.model.encoders(xs_pad, mask) |
|---|
| | | for layer_idx, encoder_layer in enumerate(self.model.encoders): |
|---|
| | | if layer_idx == len(self.model.encoders) - 1: |
|---|
| | | mask = (mask[0], vad_mask) |
|---|
| | | mask = vad_mask |
|---|
| | | encoder_outs = encoder_layer(xs_pad, mask) |
|---|
| | | xs_pad, masks = encoder_outs[0], encoder_outs[1] |
|---|
| | | |
|---|
