Skip to content

Latest commit

 

History

History
1 lines (1 loc) · 388 Bytes

README.md

File metadata and controls

1 lines (1 loc) · 388 Bytes

The initial, regular Tacotron model was trained first on LJSpeech, and then on a heavily modified version of the Ellen McClain dataset (all non-Portal 2 voice lines removed, punctuation added). The Forward Tacotron model was only trained on about 600 voice lines. The HiFiGAN model was generated through transfer learning from the sample. All models have been optimized and quantized.