| | |
|---|
| | | **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") |
|---|
| | |
|---|
| | | output_dir_v2: Optional[str] = None, |
|---|
| | | fs: dict = None, |
|---|
| | | param_dict: dict = None, |
|---|
| | | **kwargs, |
|---|
| | | ): |
|---|
| | | |
|---|
| | | hotword_list_or_file = None |
|---|
| | | if param_dict is not None: |
|---|
| | | hotword_list_or_file = param_dict.get('hotword') |
|---|
| | | |
|---|
| | | if 'hotword' in kwargs: |
|---|
| | | hotword_list_or_file = kwargs['hotword'] |
|---|
| | | |
|---|
| | | if speech2text.hotword_list is None: |
|---|
| | | speech2text.hotword_list = speech2text.generate_hotwords_list(hotword_list_or_file) |
|---|
| | | |
|---|
| | | # 3. Build data-iterator |
|---|
| | | if data_path_and_name_and_type is None and raw_inputs is not None: |
|---|
| | | if isinstance(raw_inputs, torch.Tensor): |
|---|
| | |
|---|
| | | 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) |
|---|
