raymond00000

what is meant by implicit parameter updates?

4

Hi, I am interested to try your solution. but I am not familiar to the concept of "implicit parameter updates". could you explain more on what is this meant and...

Tacotron-2 GST expected result

1

Hi, I downloaded the checkpoint from here: https://nvidia.github.io/OpenSeq2Seq/html/speech-synthesis.html#speech-synthesis I followed the tutorial to generate an example audio. My understanding is that the checkpoint was built by M-AILABS dataset. According to...

I wonder why in forward step, it returns the tdnn1_out. I suppose it should be commented else the model training will not work? def forward(self, inputs): tdnn1_out = self.tdnn1(inputs) **return...

possible to add a custom lookup dict for characters_to_jyutping

4

**Describe the bug** I read this and understand the corpora used for characters_to_jyutping are. (i) the HKCanCor corpus data included in the PyCantonese library, and (ii) the rime-cantonese data https://pycantonese.org/jyutping.html...

Quality of exact style cloning

1

Hi guys, I am very impressed with the paper's idea and result. Also, thanks a lot for sharing the codes too. I am trying the example by using Obama's voice...

in MOS, is it possible to group 1-4 questions in one block, 5 - 8 questions in next block, and so on. and for each block, the question order is...

could not train pix2pix model

1

I installed paddle paddle last month. i was trying the pix2pix. i created a dataset of 3000 images, but i faced this error during training. -------------------------------------- during training -------------------------------------- [10/29...

Hi, Sorry I am confused on the data splitting steps and codes. Please kindly correct me if I got it wrong. Omniglot has 50 classes. it allocated 30 classes in...