search

Kyubyong / dc_tts

A TensorFlow Implementation of DC-TTS: yet another text-to-speech model
Apache License 2.0
1.16k stars 370 forks source link

Anyone here has run this on Google Colab? #79

Open ghost opened 4 years ago

ghost commented 4 years ago

Right now I'm running this on Google Colab and still doesn't work. I've managed issue related to GPU runtime, batch (from 32 to 16) and slice_input_producer. Could anyone share theirs Colab's file that works? Thanks!

khush938 commented 4 years ago

Hi my file works but the thing is when I run "!python train.py 1" everything runs successfully but then it automatically quits for some reason.

ghost commented 4 years ago

Have you change the batch to 16? What do you mean by quit? I'm already set everything in place but the train.py took a lot of time, and I'm starting to doubt that this isn't working.

Crazyjoedevola commented 4 years ago

I would also like to know please. I fail at slice_input_producer If anyone can share a working note book i would be very grateful

av-pavlov commented 4 years ago

I would also like to know please. I fail at slice_input_producer

Colab's TensorFlow is v2 now, so v1 code does not work. You can try changing import tf to import tensorflow.compat.v1 as tf but there will be further problems with contrib modules.

Pawandeep-prog commented 4 years ago

I ran this on colab without any issues.

vinamramunot-tech commented 3 years ago

Has anyone tried making a custom voice dataset and trained?

vinamramunot-tech commented 3 years ago

@av-pavlov @transcriptbrain @khush938

vinamramunot-tech commented 3 years ago

Can anyone share their google colab file?

SayaliNagwkar17 commented 2 years ago

import tensorflow.compat.v1 as tf

Can you share your notebook?