采用19分钟的短音频训练CJ模型结束。运行python VC_inference.py --model_dir ./OUTPUT_MODEL/G_latest.pth --share True报错：
Traceback (most recent call last):
File "VCinference.py", line 104, in = utils.load_checkpoint(args.model_dir, net_g, None)
File "/data/VITS-fast-fine-tuning/utils.py", line 178, in load_checkpoint
model.load_state_dict(new_state_dict)
File "/opt/conda/envs/vitsFT/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1671, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for SynthesizerTrn:
size mismatch for enc_p.emb.weight: copying a param with shape torch.Size([52, 192]) from checkpoint, the shape in current model is torch.Size([68, 192]).
各位大神，这个是什么原因呢
ThornbirdZhang
commented
12 months ago
采用19分钟的短音频训练CJ模型结束。运行python VC_inference.py --model_dir ./OUTPUT_MODEL/G_latest.pth --share True报错： Traceback (most recent call last): File "VCinference.py", line 104, in
= utils.load_checkpoint(args.model_dir, net_g, None)
File "/data/VITS-fast-fine-tuning/utils.py", line 178, in load_checkpoint
model.load_state_dict(new_state_dict)
File "/opt/conda/envs/vitsFT/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1671, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for SynthesizerTrn:
size mismatch for enc_p.emb.weight: copying a param with shape torch.Size([52, 192]) from checkpoint, the shape in current model is torch.Size([68, 192]).
各位大神，这个是什么原因呢