-
Hi, you new model sounds very good, any chance you will write it up in a paper/blog-post? What's the new vocoder, it's it more WaveRNN like or wavenet like?
-
Hi, does anyone have the exception throwed, like the one described in the following stack:
Constructing model: WaveNet
Initializing Wavenet model. Dimensions (? = dynamic shape):
Train mode:…
-
The generated wave sounds are just noise after training and synthensis using default alogrithm provided in each project. I wonder which project's melsp algorithm should be used when processing, traini…
-
@Rayhane-mamah Really appreciating your contributions, thank you a lot!
And I wonder:
How long does it take to synthesize a sentence with WaveNet vocoder?
Can it be real time if the repo is implem…
-
With modern machine learning, there are better ways of TTS.
- https://github.com/CorentinJ/Real-Time-Voice-Cloning
- https://github.com/andabi/deep-voice-conversion
- https://github.com/r9y9/wavene…
-
How do I solve this error when executing the last cell?
---------------------------------------------------------------------------
AttributeError Traceback (most recent…
-
我用 [Rayhane-mamah的wavenet](https://github.com/Rayhane-mamah/Tacotron-2)训练了2000k+步效果依然很差loss -3.7左右震荡现在，设置的是高斯分布拟合，不知道是不是 r9y9的wavenet和这个不一样吗？还是前辈参数有什么不同的地方。。可以请教下吗，以及前辈有尝试过训练前者的wavenet-vocoder吗，还是直接选择…
-
Hi, I would like to train wavenet_vocoder with multi-speaker Dataset such as LibriSpeech clean data which has around 400 plus speakers. Could you please guide how to use such multi-speaker data.
-
@miaoYuanyuan
thank you for your work and for mention me also.
but this is the code . How i can help from it to use AutoVa technic ?
If you can guide me?
thanks
-
When running demo.ipynb, I am presented with this error:
>AttributeError Traceback (most recent call last)
> in ()
> 10 os.makedirs('results')
> 11
>--->…