Karan Thakkar
Karan Thakkar
Here one error because of the test case set up. We return 3 values from model now to train the discriminator.
On https://github.com/carankt/FastSpeech2.git Check the ```Generate_FileList.ipynb``` Hope it Helps!
@binarythinktank clone the repo and then run. The notebook requires a module from the repo located in `utils/files`
Take the latest version of the repo. Added the missing module.
The filelist you generated using my repo uses different symbols than this one. You must make adjustments to the filelist or the type of symbols in this repo to move...
The audio is not being generated here. That is why it is throwing a NoneType error. Check demo.iypnb, or try printing the audio shape before .T or transpose.
check the type of user you are while you cmd to install/upgrade. I was using numba with librosa and got this error, I removed numba and reinstalled librosa. It worked...
I am facing a similar issue too
https://github.com/NVIDIA/pix2pixHD/compare/master...WenliangDu:master . Check out the changes here, I made these changes and it worked.