Merge pull request #58 from alibaba-damo-academy/dev

zhifu gao

2023-02-03 79bd015ab0ded4e5aed1b1ecf32fcbc84eefde68

 funasr/bin/asr_inference_uniasr.py

@@ -96,11 +96,14 @@
        else:
            decoder = asr_model.decoder2

        ctc = CTCPrefixScorer(ctc=asr_model.ctc, eos=asr_model.eos)
        if asr_model.ctc != None:
            ctc = CTCPrefixScorer(ctc=asr_model.ctc, eos=asr_model.eos)
            scorers.update(
                ctc=ctc
            )
        token_list = asr_model.token_list
        scorers.update(
            decoder=decoder,
            ctc=ctc,
            length_bonus=LengthBonus(len(token_list)),
        )

@@ -388,7 +391,7 @@
#         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]
@@ -518,6 +521,7 @@
        token_num_relax: int = 1,
        decoding_ind: int = 0,
        decoding_mode: str = "model1",
        param_dict: dict = None,
        **kwargs,
):
    assert check_argument_types()
@@ -571,6 +575,7 @@
    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:
@@ -613,7 +618,7 @@
            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]