add sampling rate parameter

hnluo

2023-02-05 e6492e3c62f008bf8a3ca74df3cd4457133cb87d

 funasr/bin/asr_inference.py

@@ -368,7 +368,7 @@
#         except TooShortUttError as e:
#             logging.warning(f"Utterance {keys} {e}")
#             hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
#             results = [[" ", ["<space>"], [2], hyp]] * nbest
#             results = [[" ", ["sil"], [2], hyp]] * nbest
#
#         # Only supporting batch_size==1
#         key = keys[0]
@@ -483,6 +483,7 @@
    ngram_weight: float = 0.9,
    nbest: int = 1,
    num_workers: int = 1,
    param_dict: dict = None,
    **kwargs,
):
    assert check_argument_types()
@@ -533,6 +534,8 @@
    def _forward(data_path_and_name_and_type,
                 raw_inputs: Union[np.ndarray, torch.Tensor] = None,
                 output_dir_v2: Optional[str] = None,
                 fs: dict = None,
                 param_dict: dict = None,
                 ):
        # 3. Build data-iterator
        if data_path_and_name_and_type is None and raw_inputs is not None:
@@ -542,6 +545,7 @@
        loader = ASRTask.build_streaming_iterator(
            data_path_and_name_and_type,
            dtype=dtype,
            fs=fs,
            batch_size=batch_size,
            key_file=key_file,
            num_workers=num_workers,
@@ -575,7 +579,7 @@
            except TooShortUttError as e:
                logging.warning(f"Utterance {keys} {e}")
                hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
                results = [[" ", ["<space>"], [2], hyp]] * nbest
                results = [[" ", ["sil"], [2], hyp]] * nbest
            
            # Only supporting batch_size==1
            key = keys[0]