Korean Female Voice (전문 한국 여성 모델) Vol 10 PRO [RVC2 / KLM4 / 560Epochs]

Created: June 5, 2024
Korean Female Voice (전문 한국 여성 모델) Vol 10 PRO [RVC2 / KLM4 / 560Epochs]

This is the pro version of the existing Female Voice Vol 10. It is a model designed for guide vocals and broadcasting narration, created through original voice recording and Model training. It is recommended for those producing cover songs or composers who need to generate vocal guides. Additionally, it can be used for YouTube narration and other similar purposes.

Train info :
RVC 2 / RVMPE
560 Epochs
Batch size per GPU : 8
Total Steps :

Dataset - source Info :
52 Mins of Speech
21 Mins of Sing

Dataset - source correction :
- Pretrained by KLM 4
- Hubert

Model Link -
https://huggingface.co/SeoulStreamingStation/Share_Promodel/resolve/main/Korean_Girl_Vol10_Pro.zip?download=true

Additional Details:

Tags: No tags available

Download Link: https://huggingface.co/SeoulStreamingStation/Share_Promodel/resolve/main/Korean_Girl_Vol10_Pro.zip%3Fdownload%3Dtrue?download=true Hosted on Hugging Face

Convert this model in EasyAIVoice

Original Link: https://huggingface.co/SeoulStreamingStation/Share_Promodel/resolve/main/Korean_Girl_Vol10_Pro.zip?download=true (404 not found)

Auto-resolved Link: https://huggingface.co/SeoulStreamingStation/Share_Promodel/resolve/main/Korean_Girl_Vol10_Pro.zip%3Fdownload%3Dtrue?download=true

Voice accords

Main sonic traits

Selected-sample labels, grouped by what they describe.

Age
middle aged adult
teenage
young adult
Music use
producer tag
rap
adlibs
Style/timbre
villain
anime
dramatic
Use case
game
social
podcasts
Sample deck

Lean and sweet spot

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

top 4.99 · avg 4.37
female
18
male
0
female base · pitch 0 Quality Score 4.83 · 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...