Trang Nguyen

Results 6 issues of Trang Nguyen

It would make it easier to import the package into my main codebose. Right now I have to add MultiBench directory to the python path in order to use it.

In the paper, you mentioned that the audio input is MFCC feature but I don't see that conversion in the codebase. Did it change? What is the dimension of the...

Hi, I have a question regarding 7 frames offset for HIFI-GAN. Can you elaborate on the reason? Also, the default time offset is 160 * 7. What is 160 in...

Hi, I tried to load the pretrained model for VoxCeleb2 and LSR3 but they are missing lots of keys like `video.*`, `feats_conv.*`, etc.. Is the pretrained model not for the...

Hi, I came across your repository while searching for ways to train multiple NN models simultaneously using 1 single GPU. My model is pretty small (just 1 layer MLP) and...

If model 1 has X layers and model 2 has Y layers, did you compute XY pairwise alignment scores and then use the maximum as the alignment score between the...