Have you reproduced results mentioned in the paper

[shaojunyao]

thanks for sharing implementation of mwer, Have you reproduced results mentioned in the paper of Rohit Prabhavalkar etc. MINIMUM WORD ERROR RATE TRAINING FOR ATTENTION-BASED SEQUENCE-TO-SEQUENCE MODELS

[chenjiasheng]

My baseline model is very different from the one in this paper. However, over-fit experiment shows that the loss function works well.