Skip to content
This repository has been archived by the owner on Nov 11, 2023. It is now read-only.

对浅扩散模型在 whisper-ppg-large 作为编码器情况下的训练做了补充说明 #335

Open
wants to merge 2 commits into
base: 4.1-Stable
Choose a base branch
from

Conversation

hxdnshx
Copy link
Contributor

@hxdnshx hxdnshx commented Jul 22, 2023

在直接使用从 Diffusion-SVC 下载的预训练模型进行训练的场合,会出现以下错误:

 [*] restoring model from logs/44k/diffusion\model_0.pt
Traceback (most recent call last):
  File "train_diff.py", line 55, in <module>
    initial_global_step, model, optimizer = utils.load_model(args.env.expdir, model, optimizer, device=args.device)
  File "H:\so-vits-svc\diffusion\logger\utils.py", line 124, in load_model
    model.load_state_dict(ckpt['model'], strict=False)
  File "H:\so-vits-svc\venv\lib\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 Unit2Mel:
        size mismatch for unit_embed.weight: copying a param with shape torch.Size([256, 1024]) from checkpoint, the shape in current model is torch.Size([256, 1280]).

@KakaruHayate
Copy link
Contributor

你使用的是whisper-ppg-medium的预训练模型,对应本项目的whisper-ppg encoder
whisper-ppg-large目前还没有预训练模型

@hxdnshx
Copy link
Contributor Author

hxdnshx commented Jul 25, 2023

你使用的是whisper-ppg-medium的预训练模型,对应本项目的whisper-ppg encoder
whisper-ppg-large目前还没有预训练模型

是的,于是在这个pr里面补充了切换为从头开始训练的说明。

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants