Currently, what would be a proper way to use CTC loss in pytorch?
It seems to me “warp-ctc is out of maintain, and cudnn.ctc is 20x faster”
So how could we use cudnn CTC loss in pytorch? Thanks
Currently, what would be a proper way to use CTC loss in pytorch?
It seems to me “warp-ctc is out of maintain, and cudnn.ctc is 20x faster”
So how could we use cudnn CTC loss in pytorch? Thanks
It’s baked in to 1.0!
torch.nn.CTC loss , is this available only from 1.0 ?