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

Preprocessing blizzard 2013 data #11

Open jsonko opened 6 years ago

jsonko commented 6 years ago

Hi,

Thank you for your contribution. I've tried to train blizzard 2013 data set with your model. During preprocessing the data, I encountered the error because _max_out_length is None in datasets/blizzard2013.py (line 8)

Can I set this value as 700 defined in blizzard.py for blizzard dataset ?

Thanks in advance Jaeseung Ko

syang1993 commented 6 years ago

Hi, it depends on the dataset. For BC2013 data, if you set the max_out_length to 700, it will ignore to much data, beacuse most of the audios are longer than 700 frames. I guess you can get it to 2000.

jsonko commented 6 years ago

I checked your latest commit related this and then pre-process data again. Thank you for your kind response :)