Question about pytorch

[LJ-Hao]

parameter logits (Tensor of shape (1, 51864)) of distribution Categorical(logits: torch.Size([1, 51864])) to satisfy the constraint IndependentConstraint(Real(), 1), but found invalid values: tensor([[nan, nan, nan, ..., nan, nan, nan]], device='cuda:0')
I run whisper_real_time on a linux platform. But I get this problem, some one helps.

[LJ-Hao]

I have tried this way but it did not work.

[LJ-Hao]

!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! 1.5mm 1.5mm 1.5mm 1.5mm 1.5mm 1.5mm 1.5mm 1.5mm 1.5mm 1.5mm 1.5mm 1.5mm 1.5mm 1.5mm
I have solved this question, but I get the wrong text.

[phineas-pta]

raise issue in the repo u using

[ulatekh]

whisper_real_time is just a top-level .py file that drives the usual whisper features.

[phineas-pta]

doesnt guarantee error-free code