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

jmwang66

2023-05-16 6f7e27eb7c2d0a7649ec8f14d167c8da8e29f906

 funasr/models/e2e_diar_sond.py

@@ -22,7 +22,7 @@
from funasr.models.specaug.abs_specaug import AbsSpecAug
from funasr.layers.abs_normalize import AbsNormalize
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.losses.label_smoothing_loss import LabelSmoothingLoss, SequenceBinaryCrossEntropy
from funasr.utils.misc import int2vec

@@ -35,7 +35,7 @@
        yield


class DiarSondModel(AbsESPnetModel):
class DiarSondModel(FunASRModel):
    """
    Author: Speech Lab, Alibaba Group, China
    SOND: Speaker Overlap-aware Neural Diarization for Multi-party Meeting Analysis
@@ -115,7 +115,6 @@
        binary_labels_lengths: torch.Tensor = None,
    ) -> Tuple[torch.Tensor, Dict[str, torch.Tensor], torch.Tensor]:
        """Frontend + Encoder + Speaker Encoder + CI Scorer + CD Scorer + Decoder + Calc loss

        Args:
            speech: (Batch, samples) or (Batch, frames, input_size)
            speech_lengths: (Batch,) default None for chunk interator,
@@ -391,7 +390,6 @@
        self, speech: torch.Tensor, speech_lengths: torch.Tensor
    ) -> Tuple[torch.Tensor, torch.Tensor]:
        """Frontend + Encoder

        Args:
            speech: (Batch, Length, ...)
            speech_lengths: (Batch,)
@@ -491,4 +489,4 @@
            speaker_miss,
            speaker_falarm,
            speaker_error,
        )
        )