update repo

嘉渊

2023-05-16 c568628130ac42ebeea8cf48fe926520a31ff511

 funasr/models/e2e_asr_paraformer.py

@@ -55,9 +55,7 @@
            frontend: Optional[AbsFrontend],
            specaug: Optional[AbsSpecAug],
            normalize: Optional[AbsNormalize],
            preencoder: Optional[AbsPreEncoder],
            encoder: AbsEncoder,
            postencoder: Optional[AbsPostEncoder],
            decoder: AbsDecoder,
            ctc: CTC,
            ctc_weight: float = 0.5,
@@ -78,6 +76,8 @@
            predictor_bias: int = 0,
            sampling_ratio: float = 0.2,
            share_embedding: bool = False,
            preencoder: Optional[AbsPreEncoder] = None,
            postencoder: Optional[AbsPostEncoder] = None,
    ):
        assert check_argument_types()
        assert 0.0 <= ctc_weight <= 1.0, ctc_weight
@@ -732,9 +732,7 @@
            frontend: Optional[AbsFrontend],
            specaug: Optional[AbsSpecAug],
            normalize: Optional[AbsNormalize],
            preencoder: Optional[AbsPreEncoder],
            encoder: AbsEncoder,
            postencoder: Optional[AbsPostEncoder],
            decoder: AbsDecoder,
            ctc: CTC,
            ctc_weight: float = 0.5,
@@ -757,6 +755,8 @@
            embeds_id: int = 2,
            embeds_loss_weight: float = 0.0,
            embed_dims: int = 768,
            preencoder: Optional[AbsPreEncoder] = None,
            postencoder: Optional[AbsPostEncoder] = None,
    ):
        assert check_argument_types()
        assert 0.0 <= ctc_weight <= 1.0, ctc_weight
@@ -906,9 +906,9 @@
        self.step_cur += 1
        # for data-parallel
        text = text[:, : text_lengths.max()]
        speech = speech[:, :speech_lengths.max(), :]
        speech = speech[:, :speech_lengths.max()]
        if embed is not None:
            embed = embed[:, :embed_lengths.max(), :]
            embed = embed[:, :embed_lengths.max()]

        # 1. Encoder
        encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
@@ -1008,9 +1008,7 @@
            frontend: Optional[AbsFrontend],
            specaug: Optional[AbsSpecAug],
            normalize: Optional[AbsNormalize],
            preencoder: Optional[AbsPreEncoder],
            encoder: AbsEncoder,
            postencoder: Optional[AbsPostEncoder],
            decoder: AbsDecoder,
            ctc: CTC,
            ctc_weight: float = 0.5,
@@ -1030,6 +1028,8 @@
            predictor_weight: float = 0.0,
            predictor_bias: int = 0,
            sampling_ratio: float = 0.2,
            preencoder: Optional[AbsPreEncoder] = None,
            postencoder: Optional[AbsPostEncoder] = None,
    ):
        assert check_argument_types()
        assert 0.0 <= ctc_weight <= 1.0, ctc_weight
@@ -1277,9 +1277,7 @@
            frontend: Optional[AbsFrontend],
            specaug: Optional[AbsSpecAug],
            normalize: Optional[AbsNormalize],
            preencoder: Optional[AbsPreEncoder],
            encoder: AbsEncoder,
            postencoder: Optional[AbsPostEncoder],
            decoder: AbsDecoder,
            ctc: CTC,
            ctc_weight: float = 0.5,
@@ -1309,6 +1307,8 @@
            bias_encoder_type: str = 'lstm',
            label_bracket: bool = False,
            use_decoder_embedding: bool = False,
            preencoder: Optional[AbsPreEncoder] = None,
            postencoder: Optional[AbsPostEncoder] = None,
    ):
        assert check_argument_types()
        assert 0.0 <= ctc_weight <= 1.0, ctc_weight