Logo
Sign in
Sign up

HEESEUNG of ENHYPEN [KLM KPU II 32K]

Created: March 15, 2026
HEESEUNG of ENHYPEN [KLM KPU II 32K]

**Model Info :**
- Architecture : RVC Arch.
- Vocoder : NSF-HiFiGAN
- Sample Rate : 32kHz
- F0 Extraction : RMVPE
- Embedder : ContentVec
- Pretrain : KLM KPU II
- Precision : FP32

**Training Details :**
- Epochs : 180
- Dataset Length : 18m 50s
- Batch Size : 4

**Note :**
i combined the studio and live vocals in this model because the total duration of the studio vocals felt too short for me. if the output quality sounds bad, try lowering the feature ratio to 0.2.

**Download :**
https://huggingface.co/natanworkspace/KLM_KPU_II_Models/resolve/main/HEESEUNG_KPU_II_32K_180E.zip?download=true

Additional Details:

Tags: No tags available

Download Link: https://huggingface.co/natanworkspace/KLM_KPU_II_Models/resolve/main/HEESEUNG_KPU_II_32K_180E.zip?download=true Hosted on Hugging Face

Voice accords

Main sonic traits

Selected-sample labels, grouped by what they describe.

Age
young adult
middle aged adult
elderly
Music use
rap
background music
producer tag
Style/timbre
bright
villain
anime
Use case
social
game
documentaries
Sample deck

Lean and sweet spot

Pick a pitch, compare the Quality Score, then Run. Hold Ctrl or Cmd to select multiple pitches.

top 4.69 路 avg 3.66
female
10
male
8
female base 路 pitch 0 Quality Score 4.12 路 heard as female
Run
male
female
heard female heard male Quality Score = estimated audio quality, higher is better Ctrl/Cmd-click = select multiple pitches
Similar voices

This voice model sounds like

Nearby voices from generated samples. Pick a pitch in the Sample Deck to refresh the matches.

Finding nearby voices for this pitch...