Comments (11)
Did you find it inside
models.py
?
Yes, I found the l_length
👌
from vits2_pytorch.
Did you find it inside models.py
?
from vits2_pytorch.
I am not very clear about the l_length from SDP, is it a MSE loss?
from vits2_pytorch.
I am not very clear about the l_length from SDP, is it a MSE loss?
SDP is flow-based and should not trained with DD.
from vits2_pytorch.
Did you find it inside
models.py
?Yes, I found the
l_length
👌
What about the l_length for sdp?
should this line put outside the else part?
l_length = torch.sum((logw - logw_) ** 2, [1,2]) / torch.sum(x_mask)
I am not very clear about the l_length from SDP, is it a MSE loss?
SDP is flow-based and should not trained with DD.
Yes, but as the paper said, the MSE loss should be one part of the the SDP loss in training. is the flow loss somewhat a kind of MSE loss?
from vits2_pytorch.
So, in sdp
, we use a normalizing flow to send the discrete frame numbers (durations) to a gaussian. The l_length
in sdp
is a negative log likelihood that should be minimized in order to make sure that the flown-numbers are a sample of gaussian. During inference, we give it a noise and the text, and it gives out the durations (using reverse flow).
from vits2_pytorch.
So, in
sdp
, we use a normalizing flow to send the discrete frame numbers (durations) to a gaussian. Thel_length
insdp
is a negative log likelihood that should be minimized in order to make sure that the flown-numbers are a sample of gaussian. During inference, we give it a noise and the text, and it gives out the durations (using reverse flow).
Is that means we will get no help when adding a MSE( SDP(text, noise, reverse), d) to the sdp training loss? and the paper mensioned MSE is just for DP but not for SDP?
from vits2_pytorch.
No, we can do that by sending a gaussian noise and text to sdp, get the durations output, and then mse with the real (MAS) durations. I have not added it in the repo, but it is possible to do it easily.
from vits2_pytorch.
I think vits2 uses sdp in paper. 'z_d' is the noise for sdp.
from vits2_pytorch.
I think vits2 uses sdp in paper. 'z_d' is the noise for sdp.
Thanks for the help, I will have a try at convenience, I think evan when we add the MSE to the sdp predicted logw, it will be at the second stage when training SDP with DPD for the last 30K steps.
from vits2_pytorch.
I think vits2 uses sdp in paper. 'z_d' is the noise for sdp.
Thanks for the help, I will have a try at convenience, I think evan when we add the MSE to the sdp predicted logw, it will be at the second stage when training SDP with DPD for the last 30K steps.
from vits2_pytorch.
Related Issues (20)
- will more ckpts will be add later?
- KeyError when training the Chinese dataset HOT 4
- New feature: Deleting the old .pth files when training HOT 3
- ValueError: too many values to unpack (expected 2) HOT 5
- Checkpoint saves? HOT 1
- about duration-discriminator training objective HOT 8
- DurationDiscriminatorType error HOT 5
- how to know whether the model is fitting HOT 1
- Duration Discriminator problem HOT 18
- Training stuck HOT 18
- colab error HOT 3
- Bad quality audio when infer with custom condition HOT 1
- good, how this combine to the bert-vits2? HOT 2
- Keep training on existed checkpoint HOT 3
- Training doesn´t start when speaker IDs isn´t sequential from 0 HOT 1
- hop size issue HOT 1
- Training using SDP (and with DP by ratio?) HOT 6
- Have anyone tried to decrease the feature channels of the model?
- AlignerNet instead of MAS HOT 17
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from vits2_pytorch.