| | |
|---|
| | | |
|---|
| | | |
|---|
| | | if bias_encoder_type == 'lstm': |
|---|
| | | logging.warning("enable bias encoder sampling and contextual training") |
|---|
| | | self.bias_encoder = torch.nn.LSTM(inner_dim, inner_dim, 1, batch_first=True, dropout=bias_encoder_dropout_rate) |
|---|
| | | self.bias_embed = torch.nn.Embedding(self.vocab_size, inner_dim) |
|---|
| | | elif bias_encoder_type == 'mean': |
|---|
| | | logging.warning("enable bias encoder sampling and contextual training") |
|---|
| | | self.bias_embed = torch.nn.Embedding(self.vocab_size, inner_dim) |
|---|
| | | else: |
|---|
| | | logging.error("Unsupport bias encoder type: {}".format(bias_encoder_type)) |
|---|
| | |
|---|
| | | nbest_hyps = [Hypothesis(yseq=yseq, score=score)] |
|---|
| | | for nbest_idx, hyp in enumerate(nbest_hyps): |
|---|
| | | ibest_writer = None |
|---|
| | | if ibest_writer is None and kwargs.get("output_dir") is not None: |
|---|
| | | writer = DatadirWriter(kwargs.get("output_dir")) |
|---|
| | | ibest_writer = writer[f"{nbest_idx + 1}best_recog"] |
|---|
| | | if kwargs.get("output_dir") is not None: |
|---|
| | | if not hasattr(self, "writer"): |
|---|
| | | self.writer = DatadirWriter(kwargs.get("output_dir")) |
|---|
| | | ibest_writer = self.writer[f"{nbest_idx + 1}best_recog"] |
|---|
| | | |
|---|
| | | # remove sos/eos and get results |
|---|
| | | last_pos = -1 |
|---|
| | | if isinstance(hyp.yseq, list): |
|---|
