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,
@@ -740,7 +752,7 @@
                "{}.resnet{}_dense.weight".format(tensor_name_prefix_torch, layer_idx):
                    {"name": "{}/resnet{}_dense/kernel".format(tensor_name_prefix_tf, layer_idx),
                     "squeeze": None,
                     "transpose": (3, 2, 0, 1) if layer_idx == 0 else (1, 0),
                     "transpose": (2, 1, 0) if layer_idx == 0 else (1, 0),
                     },
                "{}.resnet{}_dense.bias".format(tensor_name_prefix_torch, layer_idx):
                    {"name": "{}/resnet{}_dense/bias".format(tensor_name_prefix_tf, layer_idx),
@@ -831,11 +843,11 @@
                            name, data_tf.size(), name_tf, var_dict_tf[name_tf].shape
                        ))
                    else:
                        var_dict_torch_update[name] = torch.Tensor(map_dict[name]).type(torch.int64).to("cpu")
                        var_dict_torch_update[name] = torch.from_numpy(np.array(map_dict[name])).type(torch.int64).to("cpu")
                        logging.info("torch tensor: {}, manually assigning to: {}".format(
                            name, map_dict[name]
                        ))
                else:
                    logging.warning("{} is missed from tf checkpoint".format(name))

        return var_dict_torch_update
        return var_dict_torch_update