GGaryuk

Hi, I am also running into the same issue as you guys. I am using a subset of the AVSpeech dataset. The network seems to be hard stuck at 0.69....

Hi @Mayur28, I guess it would be better to leave the mel_step_size as it was at 16. To get the proper mel spectrogram you have to load more of the...

@vokshin > What follows from this? Out of sync. I wrote a simple bash script that validates the data after preprocess.py has processed it. It traverses the directories and divides...