search

NVIDIA / tacotron2

Tacotron 2 - PyTorch implementation with faster-than-realtime inference
BSD 3-Clause "New" or "Revised" License
5.12k stars 1.39k forks source link

How can I not use the pretrained model #509

Closed Edward205 closed 3 years ago

Edward205 commented 3 years ago

I have a simple question. I dont want to use the pretrained model becuase it is in english and I dont want to train in english, I want to train in Romanian, and Romanian has extra letters. _letters = 'AĂÂBCDEFGHIÎJKLMNOPQRSȘTȚUVWXYZaăâbcdefghiîjklmnopqrsștțuvwxyz' If i try to start training I get this error: 

RuntimeError: Error(s) in loading state_dict for Tacotron2:
    size mismatch for embedding.weight: copying a param with shape torch.Size([148, 512]) from checkpoint, the shape in current model is torch.Size([74, 512]).