Add a test for CTCLoss - Githubissues

SeanNaren / warp-ctc

Pytorch Bindings for warp-ctc

Apache License 2.0

756 stars 271 forks source link

Add a test for CTCLoss #178

Closed ysk24ok closed 3 years ago

ysk24ok commented 3 years ago

Hello. Why not add a test for forward and backward of CTCLoss ? I'm glad you review this PR.

SeanNaren commented 3 years ago

Thanks @ysk24ok but out of curiosity have you tried using the native CTCLoss function? After further experiments seems it works well enough for me!

sw005320 commented 3 years ago

Yes, we actually use both warp CTC and native PyTorch CTC. The reason is 1) backward compatibility and 2) we used to observe strange behavior more for native PyTorch CTC when we used longer sequences (probably It might be gone, now.). Now, we're trying to move to espnet2 and we want to make sure especially for the backward compatibility. If espnet2 can guarantee performance comparable to espnet1 for various applications, we may completely switch to native PyTorch CTC in the near future.

SeanNaren commented 3 years ago

Awesome, one less thing to hassle with in installation :) thanks guys!