When running server for pre-trained model, I am getting runtime errors

[tahir.khalil]

error: size mismatch for embedding.weight: copying a param with shape torch.Size([149, 256]) from checkpoint, the shape in current model is torch.Size([130, 512]).

I am using model ‘checkpoint_272976.pth.tar’ but getting the above mentioned error. Any insight into this issue would be appreciated. Thanks.

[erogol (Egolge)]

are you sure you use the right version of TTs for that checklpoint. you need to checkout the right commit hash given in the released model list

[tahir.khalil]

I downloaded the following released model:
model: Tacotron-iter-120k
dataset: LJSpeech
commit: bf7590

upon running it I am getting the following error.