-
Thanks for sharing your code. I have a question when running your code.
When training the melgan which is used to synthesis speech, there is a parameter **--load_vqvae [path-to-vqvae-ckpts]**, how sh…
-
Hi, thank you for sharing your work. I'm learning about unsupervised-speech, and running your code.
I have finished training the WV-VQVAE model, but when I try to run the infer and synthesis code, th…
-
Inputs to eager execution function cannot be Keras symbolic tensors, but found [, ]
got with TF 2.2
-
Hi there, I've been trying to run pixel snail on a custom dataset. Firstly I run:
```python train_vqvae.py ./dataset --size 128```
with a size of 128 as my GPU only has 8GB of memory. Then extra…
-
Full error:
` File "jukebox/sample.py", line 279, in
fire.Fire(run)
File "C:\Users\rfnoi\.conda\envs\jukebox\lib\site-packages\fire\core.py", line 127, in Fire
component_trace = _Fir…
-
link:
- https://arxiv.org/abs/1711.00937
- http://papers.nips.cc/paper/7210-neural-discrete-representation-learning
referenced from:
- https://twitter.com/avdnoord/status/927343112145514498
- …
-
Hi, I have a problem when I train the melgan, the best model will always be the first epoch's model. Then I check the log and find it seems can't convergence.
, and when I'm monitoring the perplexity, it never g…
-
I followed the README and when I got to the "Sampling from scratch" section and try the command, this happens:
`(jukebox) D:\Bebble\jukebox\jukebox>python jukebox/sample.py --model=5b_lyrics --name…