Closed Bahm9919 closed 2 years ago
Solved. Need to train gate from scratch like in README.
Solved. Need to train gate from scratch like in README.
How much epochs did you do? Also, what dataset did you use?
Solved. Need to train gate from scratch like in README.
How much epochs did you do? Also, what dataset did you use?
i'm using my own collecting russian dataset. For this, it was about 50 epochs. Need train not only gate, so gate doesnt matter for this problem, need train without attention, and training nflow2 solved this problem, and training with cummulative attention.
Solved. Need to train gate from scratch like in README.
How much epochs did you do? Also, what dataset did you use?
i'm using my own collecting russian dataset. For this, it was about 50 epochs. Need train not only gate, so gate doesnt matter for this problem, need train without attention, and training nflow2 solved this problem, and training with cummulative attention.
So you did full retraining from scratch? No way to fix it for pretrained models?
Solved. Need to train gate from scratch like in README.
How much epochs did you do? Also, what dataset did you use?
i'm using my own collecting russian dataset. For this, it was about 50 epochs. Need train not only gate, so gate doesnt matter for this problem, need train without attention, and training nflow2 solved this problem, and training with cummulative attention.
So you did full retraining from scratch? No way to fix it for pretrained models?
There is several ways to fix it.
use_attn_prior
to false and continue training from your checkpoint path.
First of all, thanks guys for your great work and support. I have some problem with flowtron. Especially, the model repeating itself. And provide only 4sec sentence. Even if sentence has 1 sec. So its repeating itself all 4 sec. Warmstart using Tacotron2(130k) which doesnt has this problem. And i got good results. Starting for 1 flow step.
![Screenshot_2](https://user-images.githubusercontent.com/57631814/137430576-b6fc2896-09ad-4e6f-9254-e6092be07717.png)
Hope for your helping Rafael. @rafaelvalle