Empty Generated audio

[unvaiso]

Hi,

I have trained wavenet on 109 files of hi quality french audio (no noise, each file is approx 5 seconds).
Unfortunately after 70K steps of training, I got files (called individual) that don't play out from tensorboard.
PS: I have set the silence threshold to 0 because of the hi quality.

[Tunas1337]

Has anyone ever found a solution to this?