| | |
|---|
| | | input_mask_expand_dim, 0) |
|---|
| | | return sematic_embeds * tgt_mask, decoder_out * tgt_mask |
|---|
| | | |
|---|
| | | def cal_decoder_with_predictor(self, encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, hw_list=None): |
|---|
| | | def cal_decoder_with_predictor(self, encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, hw_list=None, clas_scale=1.0): |
|---|
| | | if hw_list is None: |
|---|
| | | hw_list = [torch.Tensor([1]).long().to(encoder_out.device)] # empty hotword list |
|---|
| | | hw_list_pad = pad_list(hw_list, 0) |
|---|
| | |
|---|
| | | else: |
|---|
| | | hw_embed = self.bias_embed(hw_list_pad) |
|---|
| | | hw_embed, (h_n, _) = self.bias_encoder(hw_embed) |
|---|
| | | hw_embed = h_n.repeat(encoder_out.shape[0], 1, 1) |
|---|
| | | else: |
|---|
| | | hw_lengths = [len(i) for i in hw_list] |
|---|
| | | hw_list_pad = pad_list([torch.Tensor(i).long() for i in hw_list], 0).to(encoder_out.device) |
|---|
| | |
|---|
| | | hw_embed = h_n.repeat(encoder_out.shape[0], 1, 1) |
|---|
| | | |
|---|
| | | decoder_outs = self.decoder( |
|---|
| | | encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, contextual_info=hw_embed |
|---|
| | | encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, contextual_info=hw_embed, clas_scale=clas_scale |
|---|
| | | ) |
|---|
| | | decoder_out = decoder_outs[0] |
|---|
| | | decoder_out = torch.log_softmax(decoder_out, dim=-1) |
|---|
