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
Abrupt noise, #68
Comments
Some friends think that the reason is that the dataset is not enough and overfitting appears. |
My code is from commit f4c04e2. It is commited on Nov 10, 2018。The train costs so long time that I have not use latest code。 Does the latest code have this problem? |
Have you make the sample audio from melspectrogram or text? |
When audio is made from melspectrogram and text, the "abrupt noise" will appear. The Both conditions get the same result of noise. |
@UESTCgan Is it solved? my model has similar noise. |
I listened your sample. How many steps have you trained ? How many hours are your dataset of train ? You mean that your noise is this one : I also have this noise, but the "Abrupt noise" is more serious. It is the noise : I‘m trying the latest code of the author。The step is just 100k,it is not enough , so I'm not sure if it could solve the problem. (f4c04e2). |
My model was trained with 1100epoch. |
How many hours are your dataset of train ? |
With 8 v100 gpus in gcp vm, it takes 5 days. |
How much is your sigma ? I set it as 1.0 when I train and infer. |
Sigma is Sqrt(0.5) ~ 0.7071.... for training. Sigma is 0.66 for inference. It is default in the demo. |
But big sigma makes more reverb effect. |
I see, thank you ! |
my dataset consist of 13000 sentences and 10 hours. |
I saw you used 16k sampling rate. Isn't the sampling rate 22050 for the LJSPEECH dataset? Or does it matter? What does the segment length do? Does it have to be consistent with the sampling rate? |
Segment length is independent of sampling rate. |
We've shared a quick hack to decrease the fixed noise from model's bias in waveglow : |
Closing due to inactivity. |
Does anybody have such a problem? When it is trained for 1000k steps with LjSpeech , the "abrupt noise" appears. For example:
The audio file is :
LJ001-0007.wav_synthesis_01.zip
My config.json file is:
I used single GPU。
Look forward your help!
The text was updated successfully, but these errors were encountered: