rvc-genshin-impact / README.md
ArkanDash's picture
feat: added itto-jp
6275bbb
|
raw
history blame
1.37 kB
metadata
license: mit
language:
  - en
metrics:
  - accuracy
pipeline_tag: audio-to-audio
tags:
  - rvc

RVC Genshin Impact Japanese Voice Model

model-cover.png

RVC

Learn more about Retrieval based Voice Conversion in this link below: RVC WebUI

How to use?

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

INFO

The voice I make to make this model was ripped from the game (Up to Version 3.7).

V1 Model

This model was trained with 100 epochs, 10 batch sizes, and a 40K sample rate. Every V2 model was trained 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

(New) V2 Model

This model was trained with 100 epochs, 8 batch sizes, and a 40K sample rate. (48K Sample Rate if it get released.) Every V2 model was trained more or less around 60 minutes of character voice.

Currently has 20 models

The voice that was used in this model belongs to Hoyoverse.