| | |
|---|
| | | |
|---|
| | | # remove blank symbol id, which is assumed to be 0 |
|---|
| | | token_int = list(filter(lambda x: x != 0 and x != 2, token_int)) |
|---|
| | | if len(token_int) == 0: |
|---|
| | | continue |
|---|
| | | |
|---|
| | | # Change integer-ids to tokens |
|---|
| | | token = self.converter.ids2tokens(token_int) |
|---|
| | |
|---|
| | | **kwargs, |
|---|
| | | ): |
|---|
| | | assert check_argument_types() |
|---|
| | | ncpu = kwargs.get("ncpu", 1) |
|---|
| | | torch.set_num_threads(ncpu) |
|---|
| | | |
|---|
| | | if word_lm_train_config is not None: |
|---|
| | | raise NotImplementedError("Word LM is not implemented") |
|---|
| | |
|---|
| | | ibest_writer["token"][key] = " ".join(token) |
|---|
| | | ibest_writer["token_int"][key] = " ".join(map(str, token_int)) |
|---|
| | | ibest_writer["vad"][key] = "{}".format(vadsegments) |
|---|
| | | ibest_writer["text"][key] = text_postprocessed |
|---|
| | | ibest_writer["text"][key] = " ".join(word_lists) |
|---|
| | | ibest_writer["text_with_punc"][key] = text_postprocessed_punc |
|---|
| | | if time_stamp_postprocessed is not None: |
|---|
| | | ibest_writer["time_stamp"][key] = "{}".format(time_stamp_postprocessed) |
|---|
