How many epochs does DeepSpeech2 need to converge on LibriSpeech

[Some-random]

I read the issue regarding the performance of DeepSpeech2 and noticed the CER result reported by @Soonhwan-Kwon is 0.15648 at epoch 3.

It seems really promising so I'm trying to reproduce the result. But right now I'm at epoch 5 and my validation CER (vali-clean and val-other) is still 0.3122.... So I'm wondering whether I did anything wrong or was that the intended result.

Also, the test other CER on LibriSpeech reported in DeepSpeech2 paper was 0.1325. Have you guys ever come close to this number? And if so, how many epochs do you need to get there?

Thanks in advance!

[Soonhwan-Kwon]

I'm middle of training bucketing model, but cer was 0.177740, 0.144390,0.126324,0.1210941 from Epoch 1 to 4 for test-clean dataset (There is no Epoch 0 result because at Epoch 0 and about 80% of data was through I accidentally powered off the server).
And I have no accuracy result for val-clean and val-other or test other yet, but I'll post them when the model is converged.

[Soonhwan-Kwon]

Can you post your cfg file or what is your training data?

[Some-random]

@Soonhwan-Kwon Thanks for your response! I checked my cfg again and realized I'm only using three bigru layers. I guess that's the reason why I'm not converging as fast as expected...

[Soonhwan-Kwon]

It's a relief you found the cause. Above accuracy was from the 5 bi-gru layers but if you have sufficient equipment please try 7-layers architecture. Thank you for your feed back.