-
Notifications
You must be signed in to change notification settings - Fork 36
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
HuggingFace Version #6
Comments
@leng-yue Thank you for your contribution. Based on the model definition in our paper, it appears that removing the final projection is necessary to achieve the desired outcome. |
Appreciate your quick update ⚡️ |
Surprisingly, adding the final projection did not cause any problems. |
To my mind, this is probably because they use the final projection with the 9th layer, which may not be in the same latent space. In this case, the final projection may not be able to inject speaker information... |
I believe removing the final projection may improve the performance of those projects. Anyway, for those who would like to use this Huggingface interface, please remove the final projection to get the correct output. |
Currently, the final_proj is just left there, and it's not called by default (in the forward). |
Very very great discussion! I converted huggingface model to onnx. Converter repo is here. |
@leng-yue how did you convert to huggingface? I trained my own version of contentvec and using the "transformers/src/transformers/models/hubert/convert_hubert_original_pytorch_checkpoint_to_pytorch.py" script to convert it, however I am getting this error message:
|
You can use this file: https://huggingface.co/lengyue233/content-vec-best/blob/main/convert.py |
@leng-yue Great! Thanks! |
Hi, lengyue, how can i convert this pth model of content to onnx? |
Check huggingface optimum. |
dear friend, could I ask the detailed steps of training a better contentvec model applied on svc task, based on the open source model? Is there any other methods except changing a bigger dataset? Thanks a lot @leng-yue |
Hello, can you share your way of converting to onnx with me? I also need it |
Thanks to the author for his/her fantastic model that nearly eliminated the timbre leaking problem.
For someone who doesn't want to use the FairSeq, I made a HuggingFace version of
content vec best legacy
: Link.The text was updated successfully, but these errors were encountered: