Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

onnx model required #9

Open
ykk648 opened this issue Jan 3, 2024 · 3 comments
Open

onnx model required #9

ykk648 opened this issue Jan 3, 2024 · 3 comments

Comments

@ykk648
Copy link

ykk648 commented Jan 3, 2024

No description provided.

@CNChTu
Copy link
Owner

CNChTu commented Jan 12, 2024

Coming Soon. In fact, we have completed the code and will upload it after testing.

@joe0327
Copy link

joe0327 commented Feb 5, 2024

Hi,How's the progress?

@deiteris
Copy link

deiteris commented Jun 16, 2024

Since there isn't much progress, I've made an ONNX model of fcpe by decoupling mel extractor and fcpe model with this script:
https://github.com/deiteris/voice-changer/blob/master-custom/server/utils/fcpe_onnx.py

It should be also possible to produce a combined model by returning float tensor instead of complex in torch.stft.
https://github.com/CNChTu/FCPE/blob/main/torchfcpe/mel_extractor.py#L136-L139

There's a good example of how it's done for RMVPE algorithm:
https://github.com/yxlllc/RMVPE/blob/main/export.py#L44-L57

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

No branches or pull requests

4 participants