mirror of
https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git
synced 2026-11-05 00:27:30 +00:00
[GH-ISSUE #821] torch.load missing keys 'config' and 'weight' #523
Labels
No labels
AMD/Intel
bug
bug
bug
colab
dependencies
documentation
duplicate
enhancement
following up
good first issue
help wanted
invalid
question
stale
stale
stale
todo list
wontfix
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
RVC-Project/Retrieval-based-Voice-Conversion-WebUI#523
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @Ruddle on GitHub (Jul 22, 2023).
Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/821
When loading a model from the dropdown "Inferencing voice:", I have a missing key error on cpt["config"] and cpt["weight"] in infer-web.py
I believe some other open issues stem from that, for instance:
or
I printed all keys of cpt just after
cpt = torch.load(person, map_location="cpu")to investigate.cpt keys :
discriminators.0.convs.0.bias discriminators.0.convs.0.weight_g discriminators.0.convs.0.weight_v discriminators.0.convs.1.bias discriminators.0.convs.1.weight_g discriminators.0.convs.1.weight_v discriminators.0.convs.2.bias discriminators.0.convs.2.weight_g discriminators.0.convs.2.weight_v discriminators.0.convs.3.bias discriminators.0.convs.3.weight_g discriminators.0.convs.3.weight_v discriminators.0.convs.4.bias discriminators.0.convs.4.weight_g discriminators.0.convs.4.weight_v discriminators.0.convs.5.bias discriminators.0.convs.5.weight_g discriminators.0.convs.5.weight_v discriminators.0.conv_post.bias discriminators.0.conv_post.weight_g discriminators.0.conv_post.weight_v discriminators.1.convs.0.bias discriminators.1.convs.0.weight_g discriminators.1.convs.0.weight_v discriminators.1.convs.1.bias discriminators.1.convs.1.weight_g discriminators.1.convs.1.weight_v discriminators.1.convs.2.bias discriminators.1.convs.2.weight_g discriminators.1.convs.2.weight_v discriminators.1.convs.3.bias discriminators.1.convs.3.weight_g discriminators.1.convs.3.weight_v discriminators.1.convs.4.bias discriminators.1.convs.4.weight_g discriminators.1.convs.4.weight_v discriminators.1.conv_post.bias discriminators.1.conv_post.weight_g discriminators.1.conv_post.weight_v discriminators.2.convs.0.bias discriminators.2.convs.0.weight_g discriminators.2.convs.0.weight_v discriminators.2.convs.1.bias discriminators.2.convs.1.weight_g discriminators.2.convs.1.weight_v discriminators.2.convs.2.bias discriminators.2.convs.2.weight_g discriminators.2.convs.2.weight_v discriminators.2.convs.3.bias discriminators.2.convs.3.weight_g discriminators.2.convs.3.weight_v discriminators.2.convs.4.bias discriminators.2.convs.4.weight_g discriminators.2.convs.4.weight_v discriminators.2.conv_post.bias discriminators.2.conv_post.weight_g discriminators.2.conv_post.weight_v discriminators.3.convs.0.bias discriminators.3.convs.0.weight_g discriminators.3.convs.0.weight_v discriminators.3.convs.1.bias discriminators.3.convs.1.weight_g discriminators.3.convs.1.weight_v discriminators.3.convs.2.bias discriminators.3.convs.2.weight_g discriminators.3.convs.2.weight_v discriminators.3.convs.3.bias discriminators.3.convs.3.weight_g discriminators.3.convs.3.weight_v discriminators.3.convs.4.bias discriminators.3.convs.4.weight_g discriminators.3.convs.4.weight_v discriminators.3.conv_post.bias discriminators.3.conv_post.weight_g discriminators.3.conv_post.weight_v discriminators.4.convs.0.bias discriminators.4.convs.0.weight_g discriminators.4.convs.0.weight_v discriminators.4.convs.1.bias discriminators.4.convs.1.weight_g discriminators.4.convs.1.weight_v discriminators.4.convs.2.bias discriminators.4.convs.2.weight_g discriminators.4.convs.2.weight_v discriminators.4.convs.3.bias discriminators.4.convs.3.weight_g discriminators.4.convs.3.weight_v discriminators.4.convs.4.bias discriminators.4.convs.4.weight_g discriminators.4.convs.4.weight_v discriminators.4.conv_post.bias discriminators.4.conv_post.weight_g discriminators.4.conv_post.weight_v discriminators.5.convs.0.bias discriminators.5.convs.0.weight_g discriminators.5.convs.0.weight_v discriminators.5.convs.1.bias discriminators.5.convs.1.weight_g discriminators.5.convs.1.weight_v discriminators.5.convs.2.bias discriminators.5.convs.2.weight_g discriminators.5.convs.2.weight_v discriminators.5.convs.3.bias discriminators.5.convs.3.weight_g discriminators.5.convs.3.weight_v discriminators.5.convs.4.bias discriminators.5.convs.4.weight_g discriminators.5.convs.4.weight_v discriminators.5.conv_post.bias discriminators.5.conv_post.weight_g discriminators.5.conv_post.weight_v discriminators.6.convs.0.bias discriminators.6.convs.0.weight_g discriminators.6.convs.0.weight_v discriminators.6.convs.1.bias discriminators.6.convs.1.weight_g discriminators.6.convs.1.weight_v discriminators.6.convs.2.bias discriminators.6.convs.2.weight_g discriminators.6.convs.2.weight_v discriminators.6.convs.3.bias discriminators.6.convs.3.weight_g discriminators.6.convs.3.weight_v discriminators.6.convs.4.bias discriminators.6.convs.4.weight_g discriminators.6.convs.4.weight_v discriminators.6.conv_post.bias discriminators.6.conv_post.weight_g discriminators.6.conv_post.weight_v discriminators.7.convs.0.bias discriminators.7.convs.0.weight_g discriminators.7.convs.0.weight_v discriminators.7.convs.1.bias discriminators.7.convs.1.weight_g discriminators.7.convs.1.weight_v discriminators.7.convs.2.bias discriminators.7.convs.2.weight_g discriminators.7.convs.2.weight_v discriminators.7.convs.3.bias discriminators.7.convs.3.weight_g discriminators.7.convs.3.weight_v discriminators.7.convs.4.bias discriminators.7.convs.4.weight_g discriminators.7.convs.4.weight_v discriminators.7.conv_post.bias discriminators.7.conv_post.weight_g discriminators.7.conv_post.weight_v discriminators.8.convs.0.bias discriminators.8.convs.0.weight_g discriminators.8.convs.0.weight_v discriminators.8.convs.1.bias discriminators.8.convs.1.weight_g discriminators.8.convs.1.weight_v discriminators.8.convs.2.bias discriminators.8.convs.2.weight_g discriminators.8.convs.2.weight_v discriminators.8.convs.3.bias discriminators.8.convs.3.weight_g discriminators.8.convs.3.weight_v discriminators.8.convs.4.bias discriminators.8.convs.4.weight_g discriminators.8.convs.4.weight_v discriminators.8.conv_post.bias discriminators.8.conv_post.weight_g discriminators.8.conv_post.weight_v iteration learning_ratethere are indeed no "config" or "weight".
I use models downloaded from https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main
that I then put individually in the "weights" folder, since they are not detected anywhere else.
Maybe the problem is here, but the wiki is not clear, and the pre-created folder named "pretrained" and "pretrained_v2" do not help, when you populate them, the dropdown of "Inferencing voice:" stays empty.
I tried with python 3.8 and 3.10, with
pip install -r requirements.txthaving no warning or errors@kuugaoke05 commented on GitHub (Jul 22, 2023):
How to use python 3.8, and 3.10?
I want to try it
@RVC-Boss commented on GitHub (Jul 26, 2023):
You need "ckpt processing"
and don't use Dxxx.pth
https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/wiki/FAQ-(Frequently-Asked-Questions)#q4how-to-share-a-modelhow-to-use-others-models