48K high-sampling Xiaofu Loli Sound RVC model
visibility 898chat_bubble_outline 0favorite 6
Updated: 26/04/04Published: 26/03/15
Inference Comparison
After Inference
0:000:00
Model Introduction
In test inference, this model recommends setting the pitch above +16.
Since the maximum pitch in RVC20240604Nvidia can be set to 16, it is recommended to set the gender factor around 0.30 to adjust according to your own situation.
In the 1006 version, since you cannot set the gender factor, it is recommended to set your pitch between 16 and 20. For other parameters, refer to the recommended parameters.
During sampling, to control background noise, the model's volume is not very high, so setting the loudness factor to 1.0 may cause the output volume to be relatively low, which is normal.
Please use plugins to increase output volume in the rack, but the model will not have background noise.
zhangzhang
inventory_20person_add0
Version Details
OriginalYes
AlgorithmRmvpe
CapabilitySupport
LanguageChina, the US, Japan, etc
Sample Rate48K
Base ModelMygf-f048k
HubertEnglish Hubert
Recommended Parameters
Threshold-60
Pitch16
Index Rate0.00
Volume Factor0.86
Sample Length1.0
Harvest Processes2
Fade Length0.12
Extra Inference Time2.92
infoFor reference only, adjust according to your input!
Related Models
No related models
Keywords
#rvc#Multilingual#Xiaofu#Model#Premium models#Loli voice
Comments
No comments yet

