Distortion of audio

[egorsmkv]

I am training pflowtts for Ukrainian with phonemes and seeing the following:

Loss is going down:

What can it be or how I can debug more about this distortion?

[syj901220]

Consider your data distribution.
If your dataset has a lot of short lengths, 3s masking loss would be devastating.
And short prompt leads to poor speaker similarity.
I try 1s prompt replication method like Hierspeech++, it doesn't work well.

[egorsmkv]

@syj901220 thanks, I'll look into the data.