How can I improve the synthesized results?

I have trained the model for 200k steps, and still, the synthesised results are extremely bad. 
<img width="694" alt="loss_curve" src="https://user-images.githubusercontent.com/75250229/169011115-e81ef9e5-087b-49f3-9b23-519c3affe337.png">
This is what my loss curve looks like.
Can you help me with what can I do now to improve my synthesized audio results? 
