Hardware - GPU (NVIDIA GeForce RTX 3090 Ti)
Hardware - CPU
Operating System: linux
Riva Version:2.16.0
Issue description:
hii, i have follwed same steps which give in
https://docs.nvidia.com/deeplearning/riva/user-guide/docs/tutorials/tts-finetune-nemo.html
this notebook, all things are done for fine tunning but after inference i am not getting proper audio quality
i use 30 minutes of datasets.
can you suggest me which point i need to change to get better audio quality
i already fine tune with 15000 steps with 32 batch size.
now the audio quality is very poor please help me in this