-
こんにちは。
少しwavenetについてお聞きしたいのですが、wavenetとは複数の音声を学習させることによって任意の音声を生成することが出来る技術なのでしょうか？
例)A,B,C,D,Eの音声を学習--->Fという音声を生成 ということでしょうか？
また、生成される音声は学習させる音声データに依存するのでしょうか？
最後になんですが、生成した音声でテキストを読ませることは可能なので…
-
Traceback (most recent call last):
File "C:\Users\Administrator\Desktop\Graph-WaveNet-master\train.py", line 177, in
main()
File "C:\Users\Administrator\Desktop\Graph-WaveNet-master\train.…
-
I am experimenting with training different models using different configs. Right now I am using Reflow from v2. But this problem occur in every config/models that I training with.
I noticed that th…
A-2-H updated
1 month ago
-
Thank you so much for your effort and sharing.
How can I train the clari_wavenet? By running train_student.py, isn't it?
I have read your code, and I think running train.py is just original Wavene…
-
Wavenet is calling temporal_convolution_layer which throws an exception (something about int vs. float tensor expected).
Can be workaround by setting casual=False.
Can you please fix?
-
-
Any discussions, questions and others are welcome here!
dhgrs updated
6 years ago
-
[wave_pretrained.z01.pptx](https://github.com/JasonWei512/Tacotron-2-Chinese/files/4006811/wave_pretrained.z01.pptx)
[wave_pretrained.z02.pptx](https://github.com/JasonWei512/Tacotron-2-Chinese/files…
-
To train both models sequentially (one after the other):
python train.py --model='Tacotron-2'
Feature prediction model can separately be trained using:
python train.py --model='Tacotron'
c…
-
Since this project is still in planning stage, I guess we are more open for new ideas. The README mentioned the LSTM, but Wavenet yields better results than LSTM accoring to DeepMind's paper. The Wave…