TESRS

<center> RVC Genshin Impact Japanese Voice Model

About Retrieval based Voice Conversion (RVC)

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

How to use?

Download the prezipped model and put to your RVC Project.

Model test: Google Colab / RVC Models New (Which is basically the same but hosted on spaces)

<center> INFO

Model Created by ArkanDash<br /> The voice that was used in this model belongs to Hoyoverse.<br /> The voice I make to make this model was ripped from the game (3.6 - 4.0).

News

• Currently am unable to train genshin model due to Google has recently taken actions to restrict the usage of the RVC code. In the meantime I will try to find alternative way to train other genshin model.

Total Models: 56 Models

Total Character Model: 52 Models

V1 Models: 19 <br /> V2 Models: 37

Duplicate model but different version:

• Zhongli, Nahida, Ayaka, Nilou

Plans:

• Character from fontaine.
• v2 model recreation from v1 model.

Note:

• For faruzan, somehow the index file is smaller, Might retrain faruzan. Error message: Converged (lack of improvement in inertia) at step 1152/48215 <br />
• Furina has only 20 minutes of dataset. (Will update the model in the future when its 1 hour long)
• New model will be created using v2 training, I'm no longer making v1 model.

Have a request?<br /> I accept genshin character request if you want it. Other request outside playable character:<br />

• Greater Lord Rukkhadevata: 750 Epochs, 16 Batch size, 48k Sample rate. (10 minutes dataset)
• Charlotte: 400 Epochs, 16 Batch size, 48k Sample rate. (18 minutes dataset)
• La Signora: 1k Epochs, 16 Batch size, 48k Sample rate. (8 minutes dataset)

<center> Model Training Information

V1 Model Training <br />

This was trained on Original RVC.

Pitch Extract using Harvest.<br /> This model was trained with 100 epochs, 10 batch sizes, and a 40K sample rate (some models had a 48k sample rate).

Every V1 model was trained more or less around 30 minutes of character voice.

V2 Model Training <br />

This was trained on Mangio-Fork RVC.

Pitch Extract using Crepe.<br /> This model was trained with 100 epochs, 8 batch sizes, and a 48K sample rate. (some models had a 40k sample rate).

Every V2 model was trained more or less around 60 minutes of character voice.

Warning

I'm not responsible for the output of this model. Use wisely.