This is the checkpoint of the H/ASP speaker encoder that is compatible with Coqui TTS. This speaker encoder was used on YourTTS and XTTS papers.
Please refer to the original repository: https://github.com/clovaai/voxceleb_trainer/
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.