Present Arabic training results, not so good

I make train tacotron2 + MelGan like the original notebook. I use public corpus 4 hours.
MelGan alone sound good, tacotron alone sound not so good and combination sound very bad. Can listen here. (858.0 KB)

Is make modles + config + notebook here:

Appreciate help very much

what is the dataset?

also you need to give permission for your notebook.

Is make share here:

DB is get here:

still it asks for permission :frowning:

Please make try now

your notebook fetched data from your GDrive and it is not there for us. Therefore cannot see the arabic model.

I make shared here: