RuntimeError: Error(s) in loading state_dict for Tacotron:
size mismatch for encoder.embedding.weight: copying a param with shape torch.Size([70, 512]) from checkpoint, the shape in current model is torch.Size([66, 512]).
这个错误怎么解决，设置了use_gst = False,已经消除几个了，还有一个，怎么解决呢
3条答案
按热度按时间wlp8pajw1#
#37
hwazgwia2#
感谢反馈，但是我硬是没找到这个文件
synthesizer/utils/symbols.py
yr9zkbsy3#
附上详细错误
Traceback (most recent call last):
File "C:\Users\91096\Desktop\MyFile\smilatevoices\speekChinese\toolbox_init_.py", line 262, in synthesize
specs = self.synthesizer.synthesize_spectrograms(texts, embeds, style_idx=int(self.ui.style_slider.value()), min_stop_token=min_token, steps=int(self.ui.length_slider.value())*200)
File "C:\Users\91096\Desktop\MyFile\smilatevoices\speekChinese\synthesizer\inference.py", line 93, in synthesize_spectrograms
self.load()
File "C:\Users\91096\Desktop\MyFile\smilatevoices\speekChinese\synthesizer\inference.py", line 71, in load
self._model.load(self.model_fpath, self.device)
File "C:\Users\91096\Desktop\MyFile\smilatevoices\speekChinese\synthesizer\models\tacotron.py", line 547, in load
self.load_state_dict(checkpoint["model_state"], strict=False)
File "C:\Users\91096\Envs\python37\lib\site-packages\torch\nn\modules\module.py", line 1498, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for Tacotron:
size mismatch for encoder.embedding.weight: copying a param with shape torch.Size([70, 512]) from checkpoint, the shape in current model is torch.Size([75, 512]).