Comments (1)
The w/o augmentation in our ablation study is pretty much training all components together. We didn't specifically test training together, but we believe there should be no difference between training everything together and w/o augmentation because in most TTS systems the decoder does not depend on the gradient of variance predictor (there is a nograd
operation after the text encoder output). When the decoder converges, the predictor should also converge, the same as in stage 2 of training, but we are not sure exactly what will happen.
You can also train two stages together with augmentation. It is not impossible to apply the duration-invariant data augmentation when you train them E2E, although you will need the decoder output with stretched or compressed representations to reconstruct the mel-spectrogram. If your decoder is not well-trained, however, this will derail the predictor and make it converge slower or maybe to a worse minimum, so I don't believe it should be better than 2-stage training as there is a nograd
operation to the predictor (i.e., no other components need the gradient from predictor).
If you do not apply nograd
operation, I don't know what will happen. You may try it and see. However, I do believe there is a reason why nograd
operation is applied in most TTS systems between the variance predictor and the rest of the components. This is likely because the F0 predicted by the variance predictor cannot be exactly the ground truth F0, so if you force the decoder to reconstruct the mel-spectrogram with incorrect F0 and also force it to reconstruct with correct F0, it will find a point in-between as the optimal solution and lead to worse sound quality, or may not use the F0 information at all.
from styletts.
Related Issues (20)
- About train on Vietnamese Dataset HOT 1
- 多卡训练的问题 HOT 5
- batch size and number of epochs for large dataset HOT 1
- style encoder inconsistency HOT 1
- First stage alignment training failed when TMA_CEloss=True HOT 2
- what is the mean=-4 and std=4 meannig? HOT 1
- Training the model HOT 1
- Training Model with new Dataset
- The pronunciations of single words or short words is poor? HOT 1
- Question: Fine tuning LibriTTS with StyleTTS HOT 5
- Inference exact time for each word HOT 5
- train on ESD HOT 1
- Pre-training model sound quality issues HOT 5
- question HOT 2
- StyleTTS 2 HOT 1
- S2S HOT 1
- Has anyone had this problem when converting to onnx?
- Is the uv detector trained in the pretrained pitch detector?
- Marathi Support ?
- Voice Quality issue using Librispeech
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 styletts.