Multi-speaker English VITS model. Mirror of the Coqui TTS community model
tts_models/en/vctk/vits, trained on the CSTR VCTK corpus
(University of Edinburgh, CC BY 4.0).
Files
model.pth — VITS weights
config.json — model config
speaker_ids.json — VCTK speaker ID mapping
Usage
Load with coqui-tts by passing model_path=model.pth and config_path=config.json.
