PL-BERT
PL-BERT copied to clipboard
yl4579
Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions
Refactored code for improved readability and performance, removed unused code, and added PyCharm .idea directory to .gitignore.
Hello, I am trying to train PL-BERT on the styletts2-community/multilingual-pl-bert dataset. However, the current training code does not work with this dataset. Could you please provide guidance on how to...
Please provide the steps required to train the PL-bert model for new languages (say for example: Hindi). How to prepare the dataset for that.
How to train PL-Bert for a new language? what are the steps that need to be followed? specifically for "Hindi" language.
I am training PLBERT for 5000000 number of epochs but my loss in not decreasing and always giving 8.something. Please let us know the ideal range of loss for PLBERT...