Elly has an ultra-cute doll (loli) voice
Inference Comparison
After Inference
Model Introduction
A few days ago, a model was released, also featuring a loli voice a cute loli voice (clip) for Xixi
Today, I practiced another super cute doll tone. Compared to the former, Elly's voice is more immature, with a coquettish tone, but it's not tight.
The dataset for this training was about 30 minutes long, with the dataset streamlined to around 20 minutes. It had no noise or distortion, and could sing. Below are several reasoning segments showing the results.
No reasoning has been
made <!--[if lt IE 9]>document.createElement('audio');<![endif]-->After reasoning
Miaoyin has tested that girls' original timbre needs to be adjusted to +2 or higher. If your original tone is close to a doll's tone, you can skip the pitch adjustment and adjust it according to your own needs.
Song Reasoning (1).
The original tone is a mature woman's tone; here, the reasoning pitch is +2
Song Reasoning (2).
The original tone is a loli tone; here, the inference tone is 0
parameters
Tone change: 0
Singing: Support
Language: Medium
Algorithm: rmvpe
Training: 200
Sampling rate: 44K
training log
![Image[1]-Miaoyin-RVC Sound Model Workshop](https://apis.klrvc.com/wp-content/uploads/2024/08/20240805163825677-WX20240805-160327-300x191.png)
User 3433232376
Version Details
Recommended Parameters
Related Models
Keywords
Comments
No comments yet

