Closed robrechtme closed 5 years ago
It has been quite some time ago and I'm sorry I am afraid the proper config is lost. Also T2T has some regressions over time, they overoptimize for translation config but g2p might be worse. I would try the following: play with learning rate and batch size, don't rely on early stop, train for more iterations. I might check this, but it will not be fast.
Thank you for the report.
Thanks for your clarification.
According to Tensorboard, the models could indeed be trained a bit longer. I'll look into it if I have the time.
OK, after a lot of experimenting I finally managed to receive similar results:
Cool, please provide us the details of your training.
When I run the metrics of the pretrained model, using the Phonetisaurus test split I get:
Which is what I expected.
However, when I train my own model with the training data provided with Phonetisaurus, I am not able to replicate the results:
I used the same configuration: 3 layers, 256 units and trained until early stopping at 200k steps. Why am I getting this big performance difference?