合成失败 size mismatch for encoder_proj.weight: copying a param with shape torch.Size([128, 1024]) from checkpoint, the shape in current model is torch.Size([128, 512]).

File "G:\Labs\MockingBird\.venv385\lib\site-packages\torch\nn\modules\module.py", line 1051, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for Tacotron:
size mismatch for encoder_proj.weight: copying a param with shape torch.Size([128, 1024]) from checkpoint, the shape in current model is torch.Size([128, 512]).
size mismatch for decoder.attn_rnn.weight_ih: copying a param with shape torch.Size([384, 1280]) from checkpoint, the shape in current model is torch.Size([384, 768]).
size mismatch for decoder.rnn_input.weight: copying a param with shape torch.Size([1024, 1152]) from checkpoint, the shape in current model is torch.Size([1024, 640]).
size mismatch for decoder.stop_proj.weight: copying a param with shape torch.Size([1, 2048]) from checkpoint, the shape in current model is torch.Size([1, 1536]).

我用的是 目前git的版本，模式加载的是 my_run8_25k.pt
在合成的时候报以上错误，请问是什么原因？
跟torch的版本有关系吗？
我的系统是win10 gtx1070 cuda的版本是10.1 torch的版本是1.7.1+cu101

Start at the Tacotron state_dict loading path and compare the architecture expected by the current git version with my_run8_25k.pt. Reproduce the failure using the reported Windows 10, Python, PyTorch 1.7.1+cu101, and CUDA 10.1 environment; done means identifying the compatibility requirement and documenting the matching configuration or model.

Written by the indexing model from the issue text.