tensorflow-wavenet
A TensorFlow implementation of DeepMind's WaveNet paper (by ibab)
nv-wavenet
Reference implementation of real-time autoregressive wavenet inference (by NVIDIA)
| tensorflow-wavenet | nv-wavenet | |
|---|---|---|
| 4 | 2 | |
| 5,403 | 700 | |
| - | - | |
| 0.0 | 0.0 | |
| 11 months ago | over 3 years ago | |
| Python | Cuda | |
| MIT License | BSD 3-clause "New" or "Revised" License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
tensorflow-wavenet
Posts with mentions or reviews of tensorflow-wavenet.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2021-10-14.
-
Never-ending dependency conflicts
But I'm trying to download and run python projects now - specifically this one: https://github.com/ibab/tensorflow-wavenet
-
Trying to get tensorflow wavenet github clone running and trained on my own dataset in Amazon Sagemaker Studio Lab but have run into some errors. Help would be greatly appreciated.
I've started using Amazon Sagemaker Studio Lab and the courses they offer with the interactive Jupyter Notebooks, but I'm taking a break from the theoretical stuff and math it's having me learn as preliminaries and wanted to actually see some ML in action. So I found this github I'm interested in using, downloaded/uploaded my own database of .wav files to train it with, and I've run into some issues. (I'm trying to get https://github.com/ibab/tensorflow-wavenet to work).
-
Loss diverging after converging
Yes I'm using Adam. I just saw this Issue on Github which looks similar to my Problem so I'm gonna try what they tried.
-
Why do I not see performance increases with more GPUs?
Which is based on this: https://github.com/ibab/tensorflow-wavenet
nv-wavenet
Posts with mentions or reviews of nv-wavenet.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-06-19.
-
Rust for ML?
At some point I started learning CUDA because I wanted to build a memory resident version of Wavenet (because the auto-regression of the original formulation made it to slow that it took minutes for a few seconds of audio on GPU). But before I even started the project itself there was already https://github.com/NVIDIA/nv-wavenet and even more - GAN-based models which were running on CPU in realtime without any specific tuning.
-
Why do I not see performance increases with more GPUs?
Which implementation are you using? Did you try nv-wavenet from Nvidia? Check point 4 under "Try it" here
What are some alternatives?
When comparing tensorflow-wavenet and nv-wavenet you can also consider the following projects:
WaveNet - Colab for WaveNet.
Rust-Keras-Like - pure rust implementaion for deep learning library like keras
Perceptrons
the-algorithm