IAHispano / Applio

A simple, high-quality voice conversion tool focused on ease of use and performance.
https://applio.org
MIT License
1.49k stars 247 forks source link

Error when load italia pretrain(https://huggingface.co/TheStinger/itaila)[BUG] #382

Closed CNMajest closed 5 months ago

CNMajest commented 5 months ago

Loaded pretrained_G D:\Applio-3.1.1\logs\ItaliaPreT\ItaIla_32k_G.pth Process Process-1: Traceback (most recent call last): File "D:\Applio-3.1.1\rvc\train\train.py", line 205, in run latest_checkpoint_path(hps.modeldir, "D*.pth"), net_d, optim_d File "D:\Applio-3.1.1\rvc\train\utils.py", line 86, in latest_checkpoint_path x = f_list[-1] IndexError: list index out of range

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "D:\Applio-3.1.1\env\lib\multiprocessing\process.py", line 315, in _bootstrap self.run() File "D:\Applio-3.1.1\env\lib\multiprocessing\process.py", line 108, in run self._target(*self._args, **self._kwargs) File "D:\Applio-3.1.1\rvc\train\train.py", line 220, in run net_g.module.load_state_dict( File "D:\Applio-3.1.1\env\lib\site-packages\torch\nn\modules\module.py", line 2152, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for SynthesizerTrnMs768NSFsid: size mismatch for dec.noise_convs.0.weight: copying a param with shape torch.Size([256, 1, 64]) from checkpoint, the shape in current model is torch.Size([256, 1, 80]). size mismatch for dec.ups.0.parametrizations.weight.original1: copying a param with shape torch.Size([512, 256, 20]) from checkpoint, the shape in current model is torch.Size([512, 256, 24]). size mismatch for dec.ups.1.parametrizations.weight.original1: copying a param with shape torch.Size([256, 128, 16]) from checkpoint, the shape in current model is torch.Size([256, 128, 20]). size mismatch for enc_q.pre.weight: copying a param with shape torch.Size([192, 513, 1]) from checkpoint, the shape in current model is torch.Size([192, 1025, 1]).

CNMajest commented 5 months ago

i used sampling rate 32k pretrain as 48k, that's why the error is...