search

r9y9 / deepvoice3_pytorch

PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models
https://r9y9.github.io/deepvoice3_pytorch/
Other
1.97k stars 485 forks source link

Speaker adaption, size mismatch #203

Open deeepgandhi opened 4 years ago

deeepgandhi commented 4 years ago

UserWarning: postnet.convolutions.13.bias: may contain invalid size of weight. skipping... warn("{}: may contain invalid size of weight. skipping...".format(k)) Error(s) in loading state_dict for MultiSpeakerTTSModel: size mismatch for seq2seq.encoder.embed_tokens.weight: copying a param with shape torch.Size([149, 128]) from checkpoint, the shape in current model is torch.Size([149, 256]).

I have given the latest pre-trained model on LJ and testing speaker adaption using preprocessed files of VCTK