Torch.size mismatch in encoder and decoder. using pretrained model.

利用的是@miven的预训练模型

报错信息如下：
RuntimeError: Error(s) in loading state_dict for Tacotron:
size mismatch for encoder_proj.weight: copying a param with shape torch.Size([128, 512]) from checkpoint, the shape in current model is torch.Size([128, 1024]).
size mismatch for decoder.attn_rnn.weight_ih: copying a param with shape torch.Size([384, 768]) from checkpoint, the shape in current model is torch.Size([384, 1280]).
size mismatch for decoder.rnn_input.weight: copying a param with shape torch.Size([1024, 640]) from checkpoint, the shape in current model is torch.Size([1024, 1152]).
size mismatch for decoder.stop_proj.weight: copying a param with shape torch.Size([1, 1536]) from checkpoint, the shape in current model is torch.Size([1, 2048])

还有就是，我是小白，想问下tag 0.0.1去哪找啊...不是太懂这个tag 0.0.1是什么意思。

Start by reviewing the Tacotron pretrained-model loading path and the reported encoder_proj, decoder.attn_rnn, decoder.rnn_input, and decoder.stop_proj shape mismatches. Check how the referenced model relates to tag 0.0.1. Done means identifying a compatible model and configuration or documenting the required version relationship so the checkpoint loads without size errors.

Written by the indexing model from the issue text.