metadata

license: mit
language:
  - en
metrics:
  - accuracy
library_name: fairseq
pipeline_tag: audio-to-audio
tags:
  - rvc

RVC Genshin Impact Japanese Voice Model

RVC WebUI
Use Google Colab Or RVC Models New (Which is basically the same but hosted on spaces)

RVC V1 Model

INFO

I'm trying to phase out from RVC V1 Model to V2 Model.

I will use mangio fork to create rvc soon.

For someone who asked me to make other character, please have a patient.

The voice I make to make this model was ripped from the game. This model was trained with 100 epochs, 10 batch sizes, and a 40K sample rate. I will change to a 48K sample rate soon.

Every model that I was trained in is more or less around 30 minutes of character voice. I may exclude some models to higher epochs due to the low duration of the character's voice.

Klee 150 Epochs
Fischl 150 Epochs

Currently has 19 model

The voice pack used in this model belongs to Hoyoverse.