loaded state dict contains a parameter group that doesn't match the size of optimizer's group

[hyhzl]

Summary[问题简述（一句话）] using version v0.0.1,and pretrained model https://pan.baidu.com/s/1PI-hM3sn5wbeChRryX-RCQ 提取码：2021,but occur issue: ValueError: loaded state dict contains a parameter group that doesn't match the size of optimizer's group

wechat chatting group code expired, new one please

@babysor

[babysor]

Thanks for atting me here. I prefer to discuss here since we can focus on the issue itself. It looks that you are not using the right pretrained file for your model. pls attach more info

[hyhzl]

appreciate for your answer. encouter another issue when trying Synthesizing wav locally,by executing demo_cli.py,but having problem at final step: Caught exception: ValueError('The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()') it seems the problem of ' generated_wav = encoder.preprocess_wav(generated_wav) ' this sentence, 206 line of demo_cli.py @babysor

[hyhzl]

Loading weights at synthesizer/saved_models/mandarin/mandarin.pt Traceback (most recent call last): File "synthesizer_train.py", line 37, in train(**vars(args)) File "/jfs-cache/ai-prj/MockingBird/synthesizer/train.py", line 114, in train model.load(weights_fpath, optimizer) File "/jfs-cache/ai-prj/MockingBird/synthesizer/models/tacotron.py", line 527, in load optimizer.load_state_dict(checkpoint["optimizer_state"]) File "/jfs-cache/ai-prj/conda_env/mb/lib/python3.8/site-packages/torch/optim/optimizer.py", line 201, in load_state_dict raise ValueError("loaded state dict contains a parameter group " ValueError: loaded state dict contains a parameter group that doesn't match the size of optimizer's group

[hyhzl]

@babysor