SLM adversarial training: 3 - 6 seconds in duration? about styletts2 HOT 3 CLOSED

That 2 is actually hardcoding. This is caused by the n_down of the text aligner being 2, so the length of aligned phoneme representation is halved. I will fix it all the hardcoding later when I get time.

from styletts2.

I think your calculations are not correct. Each second is 80 frames, so 6 seconds would be 480 instead of 960, and 3 seconds would be 240 frames. Setting it to 400 to 500 corresponds to roughly 5 to 6 seconds, but you can definitely do 3 to 6 seconds too, which I personally have found no difference between them.

from styletts2.

That's very helpful, thank you! I'm still a little confused about why min_len and max_len are being divided by 2 here, though:

from styletts2.