search

CorentinJ / Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time
Other
52.44k stars 8.77k forks source link

size mismatch for encoder.embedding.weight: copying a param with shape torch.Size([75, 512]) from checkpoint, the shape in current model is torch.Size([70, 512]). #1139

Open gaozhiguo168 opened 1 year ago

gaozhiguo168 commented 1 year ago

各位大佬 在替换作者模型以后在运行报错 屏幕截图 2022-11-20 222725 如图 各位遇到过吗 麻烦指点一下 感谢

Manjil-Karki commented 1 year ago

Try changing the _characters in symbols.py file to same as they were at training.

gaozhiguo168 commented 1 year ago

Thank you very much, it's resolved