A Python/Pytorch app for easily synthesising human voices
Build with GPU support no longer available
Notes: Add clip combiner and duration options to dataset building Fix blank line handling in synthesis Fix checkpoint exporting Standardise alignment JSON
Build with GPU support no longer available
Notes: Remove waveglow Update to CUDA 11.1 to support 30 series GPU's
Add checkpoint backup system Add subtitle support
Add train/test split slider to training New multi-line synthesis feature Add max_decoder_steps slider to synthesis
Remove synonym suggestion Move vocoder upload to settings Fix checkpoint selection in training
Fix English synthesis Enable checkpoint selection for export, training & synthesis
Added support for other languages
Update Kindle extraction guide
Add advanced training options for enabling/disabling checkpoint overwriting & multi GPU
Update Pytorch version and revert CUDA to 10.2