Hyungon_Ryu

pull NGC pytorch docker image. It already included al python modules for tacotron2 and waveglowsame as flowtron.

I add additional script extract available sid. See below https://github.com/yhgon/flowtron/blob/master/inference_colab.ipynb ```python import os import sys import pandas as pd import numpy as np import random from itertools import cycle from...

@Yangyangii I config 1 or 2 batch but still have this issue. IMHO, it try to load multiple checkpoint files instead of latest one.

If you want to use GPU in mel generation in COLAB, eliminate current tensorflow 1.12r0x and re-install `tensorflow-gpu==1.9.0` However, it requires to install exactly matching CUDA libraries. so below script...

I've modified the code to use BatchNormalization with batch(32) instead of Instance Normalization below is my code the difference for generator. ``` d = BatchNormalization()(d) #d = InstanceNormalization()(d) u =...

Recently I didn't test flowtron on colab. I found same problem #150 and #156 I know there are always dependency issue with colab because of pre-installed libraries. below colab show...