Giter VIP home page Giter VIP logo

Comments (11)

OedoSoldier avatar OedoSoldier commented on June 9, 2024 1

Did you find it inside models.py ?

Yes, I found the l_length👌

from vits2_pytorch.

p0p4k avatar p0p4k commented on June 9, 2024

Did you find it inside models.py ?

from vits2_pytorch.

JohnHerry avatar JohnHerry commented on June 9, 2024

I am not very clear about the l_length from SDP, is it a MSE loss?

from vits2_pytorch.

OedoSoldier avatar OedoSoldier commented on June 9, 2024

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.

JohnHerry avatar JohnHerry commented on June 9, 2024

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.

p0p4k avatar p0p4k commented on June 9, 2024

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.

JohnHerry avatar JohnHerry commented on June 9, 2024

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).

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.

p0p4k avatar p0p4k commented on June 9, 2024

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.

p0p4k avatar p0p4k commented on June 9, 2024

I think vits2 uses sdp in paper. 'z_d' is the noise for sdp.

from vits2_pytorch.

JohnHerry avatar JohnHerry commented on June 9, 2024

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.

JohnHerry avatar JohnHerry commented on June 9, 2024

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)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.