Closed TylorShine closed 1 year ago
I used your code to compare the hubert_base and checkpoint_best_legacy_500, and your code printed "Differ Some Values!" all over the screen.
Thanks fast replying.
I'm sorry, You are right. conclusions:
checkpoint_best_500.pt
and checkpoint_best_legacy_500.pt
where you uploaded files are no problem. It's fine.hubert_base.pt
file's weights, it has the same weights as the ContentVec checkpoint_best_500.pt
, no way.
Again, thank you for your wonderful work. I'll take a break.
So far, this is the only official repo for contentvec. We have not uploaded our models to other places.
OK, I understand. Thanks for given your time to me!
Have a nice day!
Hello, thanks for your great work.
As above in the title, The 500-classes pre-trained models were probably not trained.
Detail
I have tried to extract features with using pre-trained 500-classes legacy model (
checkpoint_best_legacy_500.pt
).But I compared this extracted feature to the HuBERT base model one with output graph, seems to be same.
Here is a example input as same sound:
HuBERT (fairseq officially pre-trained hubert_base.pt)
ContentVec (checkpoint_best_legacy_500.pt)
(title is "hubert", but this is truly "checkpoint_best_legacy_500.pt"'s output)
And, I wrote a script for compare model's state_dict (gist). In this result,
hubert_base.pt
andcheckpoint_best_legacy_500.pt
are the same.This is same that
checkpoint_best_500.pt
, additional key is maybe correct for (pre-)training the ContentVec but otherhubert_base.pt
related keys' values are same.Just to be sure, I also checked the 100-classes pre-trained models named
checkpoint_best_{legacy_|}100.pt
, which was seems to trained correctly.If it exists, could you please upload the correct one?
Regards.