-
Notifications
You must be signed in to change notification settings - Fork 55
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
Inferior results trained from scratch #35
Comments
有成功复现吗 |
我卡在配环境了,你们nccl报错了吗 |
I met similar question, I resample VCTK-DEMAND/test (48000hz) to 16000hz, and the result is
and I use the default loss weight
I use the .ckpt
|
I want to ask in the terminal,
,and the bug is
I try to change the loss weight into
according to
but the bug is still. And if I remove the loss weight , the training is OK,like:
This means I can't specify the loss weight,right? |
thanks. And it's ok. |
Maybe you know how the author resample the wav into 16000hz. The .wav in the VCTK-DEMAND/test is 48000hz. I try to resample and use evaluation.py, and the result is very bad. I can't make out. The quality of generated .wav is too bad. And I use the .ckpt in the original project and the original dataset in the paper. So I think my way to resample is wrong.
|
Maybe you know how the author resample the wav into 16000hz. The .wav in the VCTK-DEMAND/test is 48000hz. I try to resample and use evaluation.py, and the result is very bad. I can't make out. The quality of generated .wav is too bad. And I use the .ckpt in the original project and the original dataset in the paper. So I think my way to resample is wrong.
|
Hello! Your paper and codes are very enlightening to me and I tried to train the model from scratch on VCTK-DEMAND dataset to reproduce the results, but I found that the results are very very bad. PESQ and SSNR are merely 2.13 and 1.12, respectively. I don't modify the codes except for changing cut_len to 1.6 and batch_size to 2 to be suitable for my limited GPU. I don't know what errors are inside my codes.
For hyper-parameters, I conducted experiments on both [0.3, 0.7, 1, 0.01] in paper and [0.1, 0.9, 0.2, 0.05] in github but results are similar. For inference, I changed variable length to 8.
Looking forward to your reply~
The text was updated successfully, but these errors were encountered: