vits icon indicating copy to clipboard operation
vits copied to clipboard

About ceiling for calculating phoneme duration

Open reppy4620 opened this issue 4 years ago • 3 comments

Is there any reason to use torch.ceil instead of torch.round or other algorithms for calculating phoneme duration?

Thank you.

reppy4620 avatar Jun 22 '21 16:06 reppy4620

Is there any reason to use torch.ceil instead of torch.round or other algorithms for calculating phoneme duration?

Thank you.

if you got a duration 0.3, torch.ceil (0.3)=1, torch.round(0.3)=0.

XierHacker avatar Jun 28 '21 02:06 XierHacker

Thank you for your opinion. but as the implementation, minimum value of duration is 1 because torch.clamp_min is applied.

an extreme case, if you got duration [1.1, 1.1, 1.1, ....], torch.ceil outputs [2, 2, 2, 2, 2....], so this duration is about 2 times longer than model expected.

reppy4620 avatar Jun 28 '21 06:06 reppy4620