@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:
- attention_norm: sigmoid vs softmax
- prenet_type: original vs bn
- loss_masking: true vs false
- enable_eos_bos_chars: false vs true