Zero-shot voice conversion trained according to the scheme described in SEED-TTS.
The VC quality is surprisingly good in terms of both audio quality and timbre similarity. We decide to continue along this pathway see where it can achieve.

TODO:

• Release code
• Release v0.1 pretrained model:
• Huggingface space demo:
• HTML demo page (maybe with comparisons to other VC models)
• Code for training on custom data
• Streaming inference
• Potential architecture improvements
• More to be added