Inconsistent result with torch.nn.CTCLoss about warp-ctc HOT 3 CLOSED

But a simple example from docs works as expected

out = torch.FloatTensor([[[0.1, 0.6, 0.1, 0.1, 0.1], [0.1, 0.1, 0.6, 0.1, 0.1]]]).transpose(0, 1).requires_grad_(True)
print(out.shape)
labels = torch.IntTensor([1, 2])
label_lengths = torch.IntTensor([2])
input_lengths = torch.IntTensor([2])

warp_ctc = CTCLoss(size_average=True)
torch_ctc = nn.CTCLoss(reduction='sum')
loss1 = warp_ctc(out, labels, input_lengths, label_lengths)
print(loss1)
loss2 = torch_ctc(out.log_softmax(2), labels, input_lengths, label_lengths)
print(loss2)

out

torch.Size([2, 1, 5])
tensor([2.4629], grad_fn=<_CTCBackward>)
tensor(2.4629, grad_fn=<SumBackward0>)

@SeanNaren any ideas about the origins of double free or corruption (!prev) (cpu) or zeros on cuda?

from warp-ctc.

import torch
import torch.nn as nn
from warpctc_pytorch import CTCLoss

out = torch.randn(368, 2, 29)
input_lengths = torch.IntTensor([119, 179])
labels = torch.randint(1, 27, size=(148,)).int()
label_lengths = torch.IntTensor([59, 89])

warp_ctc = CTCLoss()
torch_ctc = nn.CTCLoss(reduction='sum')

loss1 = warp_ctc(out, labels, input_lengths, label_lengths)
print(loss1)

loss2 = torch_ctc(out.log_softmax(2), labels, input_lengths, label_lengths)
print(loss2)

from warp-ctc.

remember follows:
torch.tensor([119, 179]) returns torch.int64 , not torch.int32
torch.randint(1, 27, size=(148,)) returns torch.int64 , not torch.int32

from warp-ctc.