Extracting Alignment from Tacotron - Cherry Pick? about forwardtacotron HOT 2 OPEN

Further testing shows that Val/Attention_Score starts to deviate when r drops according to the schedule (eg down from 5 to 3). It seems like my data set doesn't play well with the shifting outputs_per_step.

from forwardtacotron.

Hi, what's the exact schedule you are using? Usually I see a slight drop in the attention score over time, but not too much. Its also questionable whether a higher score is necessarily better, it just needs to be decent imo. In my experience it is just important to get the Tacotorn down to r=1 reduction with no attention breaks. If you post your tensorboard plot I could probably give a hint about the schedule to use. Sometimes it requires a bit of tweaking (also check if your samples contain a lot of silences).

from forwardtacotron.