-
hi, i'm trying to reproduce your tutorial with pretrained models, but there is a problem with outputting files from the wavenet - after starting infer.sh I get files 1 second long, please tell me what…
-
-
`torchaudio` is an extension library for PyTorch, designed to facilitate audio processing using the same PyTorch paradigms familiar to users of its tensor library. It provides powerful tools for audio…
-
Is there any methonds we can try?
-
I use the default setting of [4,4,4,4] in 20180510_mixture_lj_checkpoint_step000320000_ema.json for umsample parameters, and I got an error from
```
if c is not None and self.upsample_net is not No…
-
It seems there's no clean way to downgrade tensorflow on google colab, so we might need to update https://github.com/r9y9/Tacotron-2 to make it run on the latest tensorflow.
-
你好,我运行了你的代码,将tacotron_batch_size改成了48,outputs_per_step改为3,但是输出在80000代时仍未对齐;
同时,我在训练仍未结束时测试synthesize,得到的确是1:14时常的wav,里面几乎全是杂音,这是错误提示
> Loading checkpoint: logs-Tacotron-2/taco_pretrained/tacotron_…
-
http://www.dtic.upf.edu/~mblaauw/IS2017_NPSS/ This job Synthesized singing voice frame-by-frame with wavenet. Is it possible to build our model like that?
-
Could you please tell us how you generated mel spectrograms for training from .wav files? What were the parameters used?
-
did you consider the IAF(Inverse Autoregressive Flow)? the paper said the student use the iaf to generate wave in a parallelized way.