Comments (7)
Sure, the model is at https://www.dropbox.com/s/fl1vqfz6611s8zw/checkpoint234000.tar?dl=0
from gst-tacotron.
Can you share the model till now.
from gst-tacotron.
Do you have any idea now? I'm facing the same problem
from gst-tacotron.
Hi, sorry for the late reply. In my early experiments, I found only when I use some unseen reference audio, the generated sometimes would become bad.
And I think the batch size will affect the quality and stability. I also find multi-gpu training for tacotron is better than single GPU model.
I guess you can reduce the head number (better token diversity) and modify the attention mechanism as we discussed before.
from gst-tacotron.
Thanks a lot for your help - batch size seem to be the problem. I had to reduce the batch size due to memory limits - and this seem to have caused the problems.
- I will retry with batchsize >= 32 and multi-gpu if possible.
from gst-tacotron.
@ErnstTmp Did you attempt it with multi-gpu at a higher batch size? Was keen on seeing if the results were better.
from gst-tacotron.
I switched temporarily to Tacotron-2, and that works with single GPU with more memory (16 GB) and batchsize 32.
Also, I could increasing the number of parallel outputs to be able to run batchsize 32 on a 12 GB GPU.
from gst-tacotron.
Related Issues (20)
- GMM Attention HOT 5
- Some problems when preprocessing ljspeech dataset HOT 1
- Reference Encoder Padding
- where do you insert or import wav file of models voice for training?
- Why use the 'tf.layer.conv1d' for query, key transformation instead of fully connected layer?
- Error in datafeeder.py HOT 1
- Path for Reference Audio HOT 1
- erro in eval.py HOT 1
- Check failed: dnnReLUCreateBackward_F32 HOT 1
- can we synthesis speaker-A's tone with speaker-B's prosody?
- What is in reference audio path?
- Pretrained Weights HOT 1
- Unable to reproduce results
- Mumbling in synthesis HOT 1
- Regarding the trained model
- Using pre-trained model of Keithito's tacotron implementation
- Add style weights when there is no reference audio
- shape of linear_outputs is not same as while training
- training stops many seconds to create new queue of data
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 gst-tacotron.