The RVC-Nekotsuka_Bi model utilizes voice samples from Nekotsuka Bi, trained by TAO71-AI to produce vocal outputs. This model is tailored for use within the I4.0 framework and the associated RVC project, although it can work with other RVC projects too. It is crucial to note that this model is designed for audio that contains clear vocals; it will not perform well with audio that includes background noise or no vocals. The training data comprises TTS and RVC sources in English, Spanish, and Japanese. Make sure to explore the capabilities of this model for various applications.
Download:
Like it? Leave a like