- Model/dataset by: MRKMJA
- Epochs: 625
- RVC v2, RMVPE, bs 8, original pretrain
- Sample rate: 40k
- Dataset: 38 minutes

Trained on 38 minutes of vocals from her recent era. Audio includes: live at-home performances from 2020, Mariah Carey's Magical Christmas Special (2020), We Belong Together (Mimi's Late Night Valentine's Mix) (2021), a few bits from Caution (2018) and Here For It All (2025).

⏬ Download:
https://huggingface.co/mrkmja/Mariah2020s/resolve/main/Mariah2020s_byMRKMJA.zip

Credit (@MRKMJA) is always cool. 🔥

Additional Details:

Tags:

Related URL: https://huggingface.co/mrkmja/Mariah2020s/resolve/main/Mariah2020s_byMRKMJA.zip

Download Link: https://huggingface.co/mrkmja/Mariah2020s/resolve/main/Mariah2020s_byMRKMJA.zip Hosted on Hugging Face

Convert this model in EasyAIVoice

Voice accords

Main sonic traits

Selected-sample labels, grouped by what they describe.

Age

young adult

teenage

middle aged adult

Music use

music

rap

producer tag

Style/timbre

anime

villain

serious

Use case

character

social

game

Sample deck

Lean and sweet spot

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

top 5.01 · avg 4.19

female

12

male

6

female base · pitch 0 Quality Score 4.90 · heard as female

Autorun

Run

male

-16 1.59 -12 3.05 -8 4.54 -4 4.79 0 4.81 4 4.70 8 4.90 12 5.01 16 4.67

female

-16 2.90 -12 4.69 -8 4.49 -4 4.83 0 4.90 4 4.71 8 4.21 12 3.49 16 3.07

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...