tensorflow-wavenet

tensorflow-wavenet copied to clipboard

Get the speaker id out from wave file

5

Hi, Does anyone know how we can use wave-net implementation to actually return the speaker id on giving wave file as input? Instead of generating the wave file for a...

arpitbaheti

Dilated Causal Convolution is implemented differently from the paper

2

According to the following visualization of dilated causal convolutional layers, I think strides in the conv1d (after time_to_batch) should be 2(equal to the dilation) so that there is only minimum...

KyungsuKim42

I want to add a valid set in my code. So I created 2 AudioReader in train.py. But the code locks up. if there is only 1 AudioReader and`n_threads` argument...

Beronx86

Local Conditioning audio samples?

1

I am wondering if anyone on this project has created any local conditioning audio samples. Or in any way created their own local conditioning.

justking100

Is it possible to work with a multivariate time series approach?

4

Hi! First of all, I would like to congratulate you for your brilliant work. So far, I have adapted your code to work with time series, instead audio files. For...

nandofernandesneto

Testing the network on music datasets

21

I've started to play around with the [MagnaTagATune dataset](http://mirg.city.ac.uk/codeapps/the-magnatagatune-dataset). There's a small change that needs to be made to the code when training on this dataset: Because it uses mp3...

ibab

More 'articulate' sounds and Meaning of --gc_channels=x and --gc_cardinality=x

3

Hi, I have been getting some interesting results in the last few days. I'm wondering if someone can help explain a couple of things for me that I am wondering...

albertious

only noise generated

1

I generated the sine wav with pitch 200HZ of 10 S wav file and trained wavenet with 300 steps ,and the loss down to 0.001,but when i geneated the wave...

jiqizaisikao

How to end training early?

3

I'm currently on step 149 of training and I have decided I want to end training and produce a wav file as output. So, I opened a new terminal window...

RuchirB

I'm trying to use wavenet to implement audio conversion instead of audio generation, which means that I don't have to restrict learning on previous inputs, so that the network would...

ghost