| | |
|---|
| | | return segments |
|---|
| | | |
|---|
| | | |
|---|
| | | #def inference( |
|---|
| | | # batch_size: int, |
|---|
| | | # ngpu: int, |
|---|
| | | # log_level: Union[int, str], |
|---|
| | | # data_path_and_name_and_type, |
|---|
| | | # vad_infer_config: Optional[str], |
|---|
| | | # vad_model_file: Optional[str], |
|---|
| | | # vad_cmvn_file: Optional[str] = None, |
|---|
| | | # raw_inputs: Union[np.ndarray, torch.Tensor] = None, |
|---|
| | | # key_file: Optional[str] = None, |
|---|
| | | # allow_variable_data_keys: bool = False, |
|---|
| | | # output_dir: Optional[str] = None, |
|---|
| | | # dtype: str = "float32", |
|---|
| | | # seed: int = 0, |
|---|
| | | # num_workers: int = 1, |
|---|
| | | # fs: Union[dict, int] = 16000, |
|---|
| | | # **kwargs, |
|---|
| | | #): |
|---|
| | | # assert check_argument_types() |
|---|
| | | # if batch_size > 1: |
|---|
| | | # raise NotImplementedError("batch decoding is not implemented") |
|---|
| | | # if ngpu > 1: |
|---|
| | | # raise NotImplementedError("only single GPU decoding is supported") |
|---|
| | | # |
|---|
| | | # logging.basicConfig( |
|---|
| | | # level=log_level, |
|---|
| | | # format="%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s", |
|---|
| | | # ) |
|---|
| | | # |
|---|
| | | # if ngpu >= 1 and torch.cuda.is_available(): |
|---|
| | | # device = "cuda" |
|---|
| | | # else: |
|---|
| | | # device = "cpu" |
|---|
| | | # |
|---|
| | | # # 1. Set random-seed |
|---|
| | | # set_all_random_seed(seed) |
|---|
| | | # |
|---|
| | | # # 2. Build speech2vadsegment |
|---|
| | | # speech2vadsegment_kwargs = dict( |
|---|
| | | # vad_infer_config=vad_infer_config, |
|---|
| | | # vad_model_file=vad_model_file, |
|---|
| | | # vad_cmvn_file=vad_cmvn_file, |
|---|
| | | # device=device, |
|---|
| | | # dtype=dtype, |
|---|
| | | # ) |
|---|
| | | # logging.info("speech2vadsegment_kwargs: {}".format(speech2vadsegment_kwargs)) |
|---|
| | | # speech2vadsegment = Speech2VadSegment(**speech2vadsegment_kwargs) |
|---|
| | | # # 3. Build data-iterator |
|---|
| | | # loader = VADTask.build_streaming_iterator( |
|---|
| | | # data_path_and_name_and_type, |
|---|
| | | # dtype=dtype, |
|---|
| | | # batch_size=batch_size, |
|---|
| | | # key_file=key_file, |
|---|
| | | # num_workers=num_workers, |
|---|
| | | # preprocess_fn=VADTask.build_preprocess_fn(speech2vadsegment.vad_infer_args, False), |
|---|
| | | # collate_fn=VADTask.build_collate_fn(speech2vadsegment.vad_infer_args, False), |
|---|
| | | # allow_variable_data_keys=allow_variable_data_keys, |
|---|
| | | # inference=True, |
|---|
| | | # ) |
|---|
| | | # |
|---|
| | | # finish_count = 0 |
|---|
| | | # file_count = 1 |
|---|
| | | # # 7 .Start for-loop |
|---|
| | | # # FIXME(kamo): The output format should be discussed about |
|---|
| | | # if output_dir is not None: |
|---|
| | | # writer = DatadirWriter(output_dir) |
|---|
| | | # else: |
|---|
| | | # writer = None |
|---|
| | | # |
|---|
| | | # vad_results = [] |
|---|
| | | # for keys, batch in loader: |
|---|
| | | # assert isinstance(batch, dict), type(batch) |
|---|
| | | # assert all(isinstance(s, str) for s in keys), keys |
|---|
| | | # _bs = len(next(iter(batch.values()))) |
|---|
| | | # assert len(keys) == _bs, f"{len(keys)} != {_bs}" |
|---|
| | | # # batch = {k: v[0] for k, v in batch.items() if not k.endswith("_lengths")} |
|---|
| | | # |
|---|
| | | # # do vad segment |
|---|
| | | # results = speech2vadsegment(**batch) |
|---|
| | | # for i, _ in enumerate(keys): |
|---|
| | | # item = {'key': keys[i], 'value': results[i]} |
|---|
| | | # vad_results.append(item) |
|---|
| | | # |
|---|
| | | # return vad_results |
|---|
| | | |
|---|
| | | |
|---|
| | | def inference( |
|---|
