search

[2025/12/01] Licensed commercial use Zhishu Mature Lady Sound RVC model

visibility 7.5kchat_bubble_outline 0favorite 13
Updated: 26/07/11Published: 24/08/13
[2025/12/01] Licensed commercial use Zhishu Mature Lady Sound RVC model

Inference Comparison

After Inference

0:000:00

Other Inference

0:000:00

Model Introduction

Please note that version V3 is Cn_hubert version, so strictly follow the https://klrvc.com/zh/tutorial/3714 tutorial to deploy the model.

Last updated: 2025-12-01

This update strengthens articulation by adopting Cn_hubert self-supervision features to enhance articulation and speech confusion.

Note that the V3 version requires replacing the Cn_hubert and is not compatible with the V1 and V2 versions. Please follow the instructions above to replace the one.

Last updated: 2024-10-07

The

dataset is larger and the results are better. This update includes Zhijiu's nearly 2-hour pure dry tone dataset, which greatly improves inference accuracy compared to the V1 version.

This is the first collaboration between top anchor Zhijiu and Miaoyin. Zhijiu's tone is a mature female tone with Wan Sheng's timbre is somewhat similar. Early on, Miaoyin and Zhijiu participated in recording a large number of dry notes and vocal performances, including handling dry tones and vocal range , and ultimately the model was generated.

The modified model may not claim to be full-range, but it is extremely close to a full-range model. The modified model will be continuously trained later to ensure optimal results.

After you purchase a modified model, you automatically receive authorization to modify the model. The model can be used commercially (but must not be used for purposes that violate laws and regulations; otherwise, you will bear the corresponding legal risks).

No reasoning has been

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

After reasoning

Singing portion performance

Singing portion performance

parameters

Tone change: 0

Singing: Support

Language: Medium

Algorithm: rmvpe

Training: 200

Sampling rate: 44K

Training log

Image[1]-Miaoyin-RVC Sound Model Workshop

other

Although this is an authorized commercial version, please do not use it for illegal purposes, or you may face legal consequences. Also, please do not re-share the information after purchase. The model contains basic information of member buyers. If such redistribution is discovered, we will suspend your usage rights. Thank you for your understanding. Miaoyin Workshop.

zhijiu

zhijiu

inventory_20person_add0

Version Details

OriginalYes
AlgorithmRmvpe
CapabilitySupport
LanguageMandarin
Sample Rate48K
Base ModelMygf-f048k
HubertChinese Hubert

Recommended Parameters

Threshold-60
Pitch0
Index Rate0.00
Volume Factor0.86
Sample Length0.30
Harvest Processes2
Fade Length0.12
Extra Inference Time2.92
infoFor reference only, adjust according to your input!

Related Models

No related models

Keywords

#Cn_hubert#rvc#Full range#Mature woman#Zhi wine#Model#Premium#The range is good

Comments

No comments yet