search

syang1993 / gst-tacotron

A tensorflow implementation of the "Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis"
368 stars 110 forks source link

Some problems when preprocessing ljspeech dataset #33

Open Charlottecuc opened 5 years ago

Charlottecuc commented 5 years ago

Hi. Thank you very much for your nice job.

I installed tensorflow 1.4 with GPU and the other packages mentioned in requirements.txt. However, when I tried to run python3 preprocess.py --dataset ljspeech , I got the following problem: image

Then, I upgraded numpy to the newest version, the problem mentioned above was solved, but it brought up a new problem: ValueError: operands could not be broadcast together with shapes (1,1025) (0,).

Could you please tell me how to solve this?

Thank you very much!

Charlottecuc commented 5 years ago

Solved.

It seems that I shouldn't install tensorflow before installing the other packages.