This is a pretrained model text aligner for use when creating a new base model for StyleTTS 2 or Stylish TTS.
- Taken from StyleTTS 2 repo here: https://github.com/yl4579/StyleTTS2
- Training code is here: https://github.com/yl4579/AuxiliaryASR
- Paper sources the model here: https://zenodo.org/records/4541452
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support