On train I get this error: too many values to unpack (expected 2).
My dataset is a zipped metadata.csv and a wavs folder.
metadata.csv is UTF in this format:
00000|text to speak
00001|text ....
wavs folder contains:
00000.wav
00001.wav ....
Comes the error from my dataset or from anything else ?
(win10, Voice-Cloning-App-1.1.1.exe with GPU)
On train I get this error: too many values to unpack (expected 2). My dataset is a zipped metadata.csv and a wavs folder. metadata.csv is UTF in this format: 00000|text to speak 00001|text .... wavs folder contains: 00000.wav 00001.wav .... Comes the error from my dataset or from anything else ? (win10, Voice-Cloning-App-1.1.1.exe with GPU)