search

AI Xiaotu / Supports singing / Girl / Shaoyu RVC model

visibility 38chat_bubble_outline 0favorite 11
Updated: 26/08/27Published: 26/08/27
AI Xiaotu / Supports singing / Girl / Shaoyu RVC model

Inference Comparison

After Inference

0:000:00

Other Inference

0:000:00

Model Introduction

This time, we bring you a newly trained RVC Shaoyu model that supports singing and is quite friendly for singing.

This time, the sampling rate is 40K, which can reduce noise output to some extent.

For detailed singing performance and speaking reasoning, please preview the audio after reasoning.

However, it is important to note that not everyone can achieve the effect of inference audio.

Training Log

g/total

tag: loss/g/total
klrvc.com34394449545901k2k3k4k5k6k

Training Log Analysis

Training Name
mygf-xts
Sampling Rate
40k
Training Status
Finished
Training Epochs
300 / 300
Training Steps
5.6k
Save Interval
Every 30 epoch
Saved Epochs
30, 60, 90, 120, 150, 180, 210, 240, 270, 300
Recommended Best Checkpoint
epoch 295 / step 5.6k / loss/g/total 27.36
The green marker indicates the lowest loss/g/total point in this log and can be used as the recommended best checkpoint.
zhangzhang

zhangzhang

inventory_20person_add0

Version Details

OriginalYes
AlgorithmRmvpe
Capability支持
Language中/美/日
Sample Rate44K
Base ModelRVC_V2
HubertEnglish Hubert

Recommended Parameters

Threshold-60
Pitch14
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

#rvc#sing#A young girl#Attending the Lesser Palace#Model

Comments

No comments yet