Comments (7)
因为刚开始训练的时候,encoder还学的不好。encoder和diffusion都在拟合mel谱图,没有diffusion encoder也可以独立工作,整合系统甚至可以把diffusion完全删除也是可以的。等encoder学好了,在加入diffusion训练,可以节约训练时间。diffusion训两百个epoch可以看到效果。
from grad-svc.
因为刚开始训练的时候,encoder还学的不好。encoder和diffusion都在拟合mel谱图,没有diffusion encoder也可以独立工作,整合系统甚至可以把diffusion完全删除也是可以的。等encoder学好了,在加入diffusion训练,可以节约训练时间。diffusion训两百个epoch可以看到效果。
谢谢你的解答,另外有一个问题。为什么SpeakerClassifier中的说话人个数是写死的?line 292 of encoder.py
self.speaker = SpeakerClassifier( n_channels, 256, # n_spks: 256 )
from grad-svc.
256是声纹向量的维度
from grad-svc.
256是声纹向量的维度
好的,谢谢解答!
from grad-svc.
@MaxMax2016 请教一个问题,你是多卡还是单卡训练的?
我自己写了一个多卡的代码,训练速度上来了,但是mel_loss收敛的并没有单卡好。
单卡训练到250epoch大概是:
Epoch 250: | spk loss = 0.337 | mel loss = 0.330 | prior loss = 1.139 | diffusion loss = 0.097
多卡训练到250epoch大概是:
Epoch 250: | spk loss = 0.335 | mel loss = 0.335 | prior loss = 1.135 | diffusion loss = 0.099
from grad-svc.
单卡,改用多卡要调学习率的吧
from grad-svc.
单卡,改用多卡要调学习率的吧
调了学习率之后,直接跑飞了,melloss一直0.72不下降
from grad-svc.
Related Issues (16)
- A better alternative to Grad-TTS HOT 1
- 在推理阶段遇到了路径报错
- Something wrong with the decoder
- 训练数据量? HOT 1
- 电音现象问题请教 HOT 1
- What is the best version? HOT 12
- num_worker Issue
- What is the advantage for Grad-SVC, compare to So-VITS-SVC? HOT 3
- Does SVS work in english lyrics? HOT 2
- Regarding the error "Fail to allocate bitmap" during the training process HOT 4
- Error during training HOT 10
- Runtime error HOT 3
- training error HOT 5
- Setting base.yaml HOT 1
- Adjusting Hubert model
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 grad-svc.