validation wer of training mode and test mode are different.

Alexander-H-Liu / End-to-end-ASR-Pytorch

This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.

MIT License

1.18k stars 317 forks source link

validation wer of training mode and test mode are different. #64

Open burin-n opened 3 years ago

burin-n commented 3 years ago

I trained the model and got a good validation WER. However, I got very poor decoded results when I tried to load that checkpoint and ran it in --test mode.

Do you have any suggestion on this?

kouohhashi commented 3 years ago

I have a similar experience. have you find a solution?

burin-n commented 3 years ago

There is a problem with the saved checkpoint. I'm not sure what happened and how was it happen. As I found, the weights of latest.pth were not actually come from the last epoch. I retrained the model and never found this problem again.