funasr pages

游雁

2023-11-16 4ace5a95b052d338947fc88809a440ccd55cf6b4

 funasr/models/encoder/resnet34_encoder.py

@@ -406,6 +406,12 @@
            tf2torch_tensor_name_prefix_torch="encoder",
            tf2torch_tensor_name_prefix_tf="seq2seq/speech_encoder"
    ):
        """
        Author: Speech Lab, Alibaba Group, China
        SOND: Speaker Overlap-aware Neural Diarization for Multi-party Meeting Analysis
        https://arxiv.org/abs/2211.10243
        """

        super(ResNet34Diar, self).__init__(
            input_size,
            use_head_conv=use_head_conv,
@@ -633,6 +639,12 @@
            tf2torch_tensor_name_prefix_torch="encoder",
            tf2torch_tensor_name_prefix_tf="seq2seq/speech_encoder"
    ):
        """
        Author: Speech Lab, Alibaba Group, China
        TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization
        https://arxiv.org/abs/2303.05397
        """

        super(ResNet34SpL2RegDiar, self).__init__(
            input_size,
            use_head_conv=use_head_conv,
@@ -838,4 +850,4 @@
                else:
                    logging.warning("{} is missed from tf checkpoint".format(name))

        return var_dict_torch_update
        return var_dict_torch_update