980202006

How many polyphonic words are covered by these dictionaries, and can you provide some training data? @Kyubyong

Thank you!

Thank you!

The first script exported the torch onnx model, the second exported the tensorrt model, the first time I exported the same code successfully, the second time it got stuck, I...

Why do these two lines cause the model export to fail? Both the model file and the core.spectral_norm file are in the link below. https://drive.google.com/drive/folders/1SBiykgPPVzkvyy7IjACZQVw2lrxAe1Xa?usp=sharing

Thank you!

Is there any detail about the speaker embedding? Such as What model is used to generate it, whether it is pre-trained, and what data set is used

Thank you!

In addition, the mapping network training is even worse

Whether to remove the mapping network, if I only use it with reference audio.