Hui Lu

Results 3 issues of Hui Lu

Thanks for your wonderful repo! Just found this very little bug: Here if one specifies several dozens of speakers to be used for training, https://github.com/kan-bayashi/ParallelWaveGAN/blob/b9e740c67f77ff689abf32edbeff825bc7f7582e/egs/vctk/voc1/run.sh#L20 then the following line will...

wontfix

Thanks for sharing the code and you did a great job. I noticed that in the paper the downsampling process on the temporal axis is different for the forward sequence...

I'm trying to train an LPCNet vocoder on my own 16khz dataset. I want to modify the window length to 50ms and window shift to 12.5ms. I guess that I...