| | |
| | | import logging |
| | | import sys |
| | | import time |
| | | import json |
| | | from pathlib import Path |
| | | from typing import Optional |
| | | from typing import Sequence |
| | |
| | | punc_infer_config: Optional[str] = None, |
| | | punc_model_file: Optional[str] = None, |
| | | outputs_dict: Optional[bool] = True, |
| | | param_dict: dict = None, |
| | | **kwargs, |
| | | ): |
| | | assert check_argument_types() |
| | |
| | | def _forward(data_path_and_name_and_type, |
| | | raw_inputs: Union[np.ndarray, torch.Tensor] = None, |
| | | output_dir_v2: Optional[str] = None, |
| | | param_dict: dict = None, |
| | | ): |
| | | # 3. Build data-iterator |
| | | if data_path_and_name_and_type is None and raw_inputs is not None: |
| | |
| | | postprocessed_result[2] |
| | | if len(word_lists) > 0: |
| | | text_postprocessed_punc, punc_id_list = text2punc(word_lists, 20) |
| | | text_postprocessed_punc_time_stamp = "predictions: {} time_stamp: {}".format( |
| | | text_postprocessed_punc, time_stamp_postprocessed) |
| | | text_postprocessed_punc_time_stamp = json.dumps({"predictions": text_postprocessed_punc, |
| | | "time_stamp": time_stamp_postprocessed}, |
| | | ensure_ascii=False) |
| | | else: |
| | | text_postprocessed_punc = "" |
| | | punc_id_list = [] |