| | |
|---|
| | | |
|---|
| | | # bias encoder |
|---|
| | | if self.bias_encoder_type == 'lstm': |
|---|
| | | logging.warning("enable bias encoder sampling and contextual training") |
|---|
| | | self.bias_encoder = torch.nn.LSTM(self.inner_dim, |
|---|
| | | self.inner_dim, |
|---|
| | | 2, |
|---|
| | |
|---|
| | | self.lstm_proj = None |
|---|
| | | self.bias_embed = torch.nn.Embedding(self.vocab_size, self.inner_dim) |
|---|
| | | elif self.bias_encoder_type == 'mean': |
|---|
| | | logging.warning("enable bias encoder sampling and contextual training") |
|---|
| | | self.bias_embed = torch.nn.Embedding(self.vocab_size, self.inner_dim) |
|---|
| | | else: |
|---|
| | | logging.error("Unsupport bias encoder type: {}".format(self.bias_encoder_type)) |
|---|
| | |
|---|
| | | |
|---|
| | | speech = speech.to(device=kwargs["device"]) |
|---|
| | | speech_lengths = speech_lengths.to(device=kwargs["device"]) |
|---|
| | | |
|---|
| | | |
|---|
| | | # hotword |
|---|
| | | self.hotword_list = self.generate_hotwords_list(kwargs.get("hotword", None), tokenizer=tokenizer, frontend=frontend) |
|---|
| | | |
|---|
| | |
|---|
| | | 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): |
|---|
| | |
|---|
| | | token, timestamp) |
|---|
| | | |
|---|
| | | result_i = {"key": key[i], "text": text_postprocessed, |
|---|
| | | "timestamp": time_stamp_postprocessed, |
|---|
| | | "timestamp": time_stamp_postprocessed |
|---|
| | | } |
|---|
| | | |
|---|
| | | if ibest_writer is not None: |
|---|
| | | ibest_writer["token"][key[i]] = " ".join(token) |
|---|
| | | # ibest_writer["text"][key[i]] = text |
|---|
| | | ibest_writer["timestamp"][key[i]] = time_stamp_postprocessed |
|---|
| | | ibest_writer["text"][key[i]] = text_postprocessed |
|---|
| | | else: |
|---|
