search

Chiikawa (chiikawa) Hachi-Kohachi RVC model

visibility 3.2kchat_bubble_outline 0favorite 18
Updated: 26/07/01Published: 24/10/04
Chiikawa (chiikawa) Hachi-Kohachi RVC model

Inference Comparison

After Inference

0:000:00

Model Introduction

This is the Xiaoba version RVC model. If you need a GPT model, you can click the link below, which I also created myself.

The original dataset for Xiao Ba was written in Japanese, and after repeated generation and reasoning in Mandarin, this model was obtained. The model performs very well both in Mandarin and Japanese, and the original dataset is very large. Finally, I will include a roughly 30-minute Xiao Ba dataset (a pre-processed dataset) for everyone to download and create other types of models.

Note: Due to your own original timbre, please adjust the pitch to achieve the best effect.

No reasoning has been

made <!--[if lt IE 9]>document.createElement('audio');<![endif]-->

After reasoning

Japanese text has not yet been reasoned

After reasoning

sing

parameters

Tone change: 0

Algorithm: rmvpe

Singing: Support

Languages: Chinese/Japanese

Training: 200

Sampling rate: 44K

training log

Image[1]-Miaoyin-RVC Tone Model Workshop

000

Version Details

OriginalYes
AlgorithmRmvpe
CapabilitySupport
LanguageMandarin
Sample Rate44K

Recommended Parameters

Threshold0.25
Pitch0
Index Rate0.75
Volume Factor1.25
Sample Length192
Harvest Processes2
Fade Length100
Extra Inference Time500
infoFor reference only, adjust according to your input!

Related Models

No related models

Keywords

#chiikawa#rvc#Download#Two-dimensional#Lovely#Jiikawa#Xiao Ba#Model#Childhood voice

Comments

No comments yet