Merge pull request #518 from alibaba-damo-academy/dev_wjm2

jmwang66

2023-05-16 6f7e27eb7c2d0a7649ec8f14d167c8da8e29f906

 funasr/models/e2e_tp.py

@@ -17,9 +17,8 @@
from funasr.modules.add_sos_eos import add_sos_eos
from funasr.modules.nets_utils import make_pad_mask, pad_list
from funasr.torch_utils.device_funcs import force_gatherable
from funasr.train.abs_espnet_model import AbsESPnetModel
from funasr.models.base_model import FunASRModel
from funasr.models.predictor.cif import CifPredictorV3


if LooseVersion(torch.__version__) >= LooseVersion("1.6.0"):
    from torch.cuda.amp import autocast
@@ -30,7 +29,7 @@
        yield


class TimestampPredictor(AbsESPnetModel):
class TimestampPredictor(FunASRModel):
    """
    Author: Speech Lab of DAMO Academy, Alibaba Group
    """
@@ -65,7 +64,6 @@
            text_lengths: torch.Tensor,
    ) -> Tuple[torch.Tensor, Dict[str, torch.Tensor], torch.Tensor]:
        """Frontend + Encoder + Decoder + Calc loss

        Args:
                speech: (Batch, Length, ...)
                speech_lengths: (Batch, )
@@ -113,7 +111,6 @@
            self, speech: torch.Tensor, speech_lengths: torch.Tensor
    ) -> Tuple[torch.Tensor, torch.Tensor]:
        """Frontend + Encoder. Note that this method is used by asr_inference.py

        Args:
                speech: (Batch, Length, ...)
                speech_lengths: (Batch, )