Hello I am trying the translate_ende_wmt32k problem given in the walk-through. Trained the model and during inference I don't want to decode file on a whole but want to decode sentence by sentence as they come so that I load the model only once and wait for input to decode them as they come. Any help on how it could be done ?
Thanks.
Hello I am trying the
translate_ende_wmt32k
problem given in the walk-through. Trained the model and during inference I don't want to decode file on a whole but want to decode sentence by sentence as they come so that I load the model only once and wait for input to decode them as they come. Any help on how it could be done ? Thanks.