funasr/models/paraformer/model.py
@@ -33,7 +33,6 @@ def __init__( self, # token_list: Union[Tuple[str, ...], List[str]], specaug: Optional[str] = None, specaug_conf: Optional[Dict] = None, normalize: str = None, @@ -452,7 +451,7 @@ self.nbest = kwargs.get("nbest", 1) meta_data = {} if isinstance(data_in, torch.Tensor): # fbank if isinstance(data_in, torch.Tensor) and kwargs.get("data_type", "sound") == "fbank": # fbank speech, speech_lengths = data_in, data_lengths if len(speech.shape) < 3: speech = speech[None, :, :]
