Unique tone: 48k Girl Oto Kisu RVC model
visibility 1.1kchat_bubble_outline 0favorite 11
Updated: 25/11/12Published: 25/11/12
Inference Comparison
After Inference
0:000:00
Other Inference
0:000:00
Model Introduction
The language comes from Japanese, and this tone sounds quite unique, lacking a bit of a radio station feel.
This model supports a certain degree of laughter and screaming, but only to a certain extent.
From the monitors tested, the range is roughly in the C2-C4 range.
In [Other Reasoning], there is a real-time test of listening effects.
This model works better for Japanese because I used Japanese corpora. Training with mygf-f048K yields better accent optimization.
zhangzhang
inventory_20person_add0
Version Details
OriginalYes
AlgorithmRmvpe
CapabilitySupport
LanguageJapanese
Sample Rate48K
Base ModelMygf-f048k
Recommended Parameters
Threshold-60
Pitch13
Index Rate0.00
Volume Factor0.86
Sample Length0.30
Harvest Processes1
Fade Length0.12
Extra Inference Time2.92
infoFor reference only, adjust according to your input!
Related Models
No related models
Keywords
#48k#rvc#Girlish voice#Shaoyin was a young imperial musician#Tree-dwelling#Model#Live broadcast
Comments
No comments yet

