Best config for tacotron2 training

@erogol What is the best config for tacotron2 training. I see that master branch config_tacotron2.json is different from the one that comes with the latest pretrained Tacotron2 model.
In particular what are better choices:

  1. attention_norm: sigmoid vs softmax
  2. prenet_type: original vs bn
  3. loss_masking: true vs false
  4. enable_eos_bos_chars: false vs true

There is no better choice, it is all about the dataset. But it is better to start with the original Tacotron paper. So it means;