Comments (2)
The original wavenet used filter width of 2 which is why its the most common. In the parallel wavenet paper they increased sampling rate from 16kHz to 24kHz, filter width of 3 and claim better sound quality. Since the sample rate 50% faster and filter width is 50% longer, the convolution is essentially over the same amount of time. So far I have my best results with 3 width filter, 24kHz but I have not compared it to its 16kHz 2 width equivalent because it's not worth the training time.
from wavenet_vocoder.
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
from wavenet_vocoder.
Related Issues (20)
- Installation issue
- why it needs 'train.txt' in evaluate.py when I input the mel files(.npy) ?
- Error when using pretrained model with mel-sepcs from "deepvoice3-pytorch" HOT 1
- About Different Size between Predicted-mel and Preprocess-mel
- Load pretrained model state_dict error ,when run synthesis.py HOT 3
- batch_wavegen() call issue
- The speed of inference is too slow HOT 1
- Multi-speaker TTS with ESPnet mel-spectrograms
- Speech Marks HOT 2
- Train error
- Can't load data HOT 1
- Autograd-Issue for Training Gaussian WaveNet
- Slow Inference HOT 1
- Input Data and Targets while training the Wavenet using MOL
- NOT AN ISSUE: Fixed colab notebook to work as of October 14th, 2021 HOT 6
- librosa error on stage 2 of gaussian run.sh ParameterError: Audio data must be floating-point HOT 3
- spectrogram (image) to wav
- I cant even use Wavenet pre-trained HOT 1
- Cant train HOT 1
- How to training a WaveNet model with different sample rate?
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 wavenet_vocoder.