Hugging Face's logo

sparanoid
/
milky-green-sovits

Audio-to-Audio
Transformers
Chinese
English
Japanese
Inference Endpoints
Model card Files Community

Milky Green SoVITS Model

Milky Green (aka. ๆ˜Žๅ‰ๅฅถ็ปฟ) SoVITS (SoftVC VITS Singing Voice Conversion) model

  • covers_ models: trained from singing streams (recommended)
  • vocals_ models: trained from chit-chat streams (not recommended, datasets are not clean enough)
Downloads last month
7
Inference Examples
Audio-to-Audio
Inference API (serverless) does not yet support transformers models for this pipeline type.

Spaces using sparanoid/milky-green-sovits 3