Is the training process normal?

[wenku1992abc]

is it overfitting?
the train dataset loss decrease quickly,but the val_loss even no change.
as shown in the picture
@philipperemy

[wenku1992abc]

then,early stopping itself.

[philipperemy]

@wenku1992abc yes it looks like you overfitted a bit your data. Your accuracy is 99.18% and your validation accuracy is around 90%. That's why the early stopping kicked in. The model is very big so it requires a lot of data. However, I guess your training is completed. An accuracy of 90% or above can be acceptable if you train from scratch of many many speakers. If you have more data, use it!

[wenku1992abc]

thanks your reply！
by the way 1080 speaker is it less?
@philipperemy

[philipperemy]

LibriSpeech had 2484 speakers.

[wenku1992abc]

ok,thanks !