- Support `normalize-before` option in decoding - Support `log_base` option in preprocessing - Update pre-trained models
0.5.0
- Support HiFiGAN - Support StyleMelGAN - Refactored
0.4.8
- Support Pytorch 1.7 - Add JSSS recipe - Support the case where `wav.scp` and `segments` have a different number of lines
0.4.6
- Minor fix of pretrained model save directory
0.4.5
- Simplify decoding part - Add `load_model` function - Add `inference` method in each genearator - Add `download_pretraiend_model` function to download from google drive directly