v1.1.48: Major improvements.
Increased training epochs from 6 to 48.
All previous models were trained with 6 epochs. 

v1.0.0: Minor improvements.
Added another 120 padded audio clips to the dataset.
Dataset size is now 425 audio clips.

v0.2.2: Major improvements.
Added padding at the end of the audio clips.
Spelling corrections in the CSV files.

v0.2.1: Major improvements.
Manually Corrected audio clip cutoffs in the dataset.
However the dataset size was reduced to 300.

v0.1.0: First Model.
A rough model created with XTTS-Finetune's automatic dataset creator.
1,500 clips in dataset.