Tensorsize doesn't match, svc_hubert_soft_diff_svc.py about fish-diffusion HOT 10 CLOSED

I hope this is what you've meant:
print(features.shape)
print(pitches.shape)

this prints:

torch.Size([4, 608, 256])
torch.Size([4, 608, 1])

from fish-diffusion.

svc_hubert_soft_diff_svc is a very old deprecated version.

from fish-diffusion.

It seems like your features and pitches have different shapes. Can you print their shape before this line:

features += self.pitch_encoder(pitches)

from fish-diffusion.

The shape of features and pitches are correct.
Can you also print the shape of "self.pitch_encoder(pitches)" and submit your config file.

from fish-diffusion.

this:
print(features.shape)
print(pitches.shape)
print(self.pitch_encoder(pitches).shape)

prints:
torch.Size([4, 608, 256])
torch.Size([4, 608, 1])
torch.Size([4, 608, 1, 256])

the config is the default "svc_hubert_soft_diff_svc.py".
I mostly only changed the batch_size to 105 and num_workers to 10

from fish-diffusion.

Can you try configs/svc_content_vec.py instead?
I double-checked the config of svc_hubert_soft_diff_svc, and there is some issue in the pitch_to_coarse (already deprecated).

from fish-diffusion.

that one works just fine.
Isn't "svc_hubert_soft_diff_svc" supposed to be a better option or am I understanding something wrong here?

from fish-diffusion.

btw could you please create a comparison table in the Readme?
else it is really hard to know what is usable, what is older, what is more lightweight and what is more high quality.

from fish-diffusion.

Generally, newer models are better, but I think making a comparison table will be helpful. Will do it later.

from fish-diffusion.

We plan to release a comparison and other information in the next major release.

from fish-diffusion.