search

jaywalnut310 / glow-tts

A Generative Flow for Text-to-Speech via Monotonic Alignment Search
MIT License
651 stars 150 forks source link

Getting assertion error for while training #52

Closed debasish-mihup closed 3 years ago

debasish-mihup commented 3 years ago

def mel_spectrogram(self, y): assert(torch.min(y.data) >= -1) # Getting value of tensor(-34834.9805) assert(torch.max(y.data) <= 1)

I am getting assertion error in the above function in commons.py during training. Is this a issue due to incorrect training data and how to handle the issue? Any tips?

debasish-mihup commented 3 years ago

The issue is unrelated to the package. The problem was with few of the audio files as the bit rate was different.