Huening Bahiyyih (Kep1er) 350


From the creator

"I might gonna overtrain if it had good quality or something. Made by me Dataset made by me (8:57 Minutes) (2022-2023 songs from K-pop Band Kep1er includes Japanese Versions and includes 2 cover songs) Trained with crepe V2 24th RVC Model/9th RVC V2 Model. USE FEATURE RATIO TO 1.0 ALWAYS. Credit to me on Youtube & TikTok. Mangio Crepe 64 (350 Epochs): RMVPE (950 Epochs): And of course The last retrain with Mangio Crepe Extraction. My model hit the overtrain after 350 epochs I think so well. UPDATE: I retrain for RMVPE extraction The new loss is 43. Who will proof with this?"


Introducing the Huening Bahiyyih (Kep1er) 350 RVC Model, designed specifically for creating high-quality AI covers and text-to-speech outputs. This model was trained using datasets from K-pop band Kep1er's 2022-2023 discography, including Japanese versions and two cover songs. Leveraging the power of crepe V2 and RVC Model/9th RVC V2 Model, this tool ensures optimal feature ratio utilization. With training completed at 350 epochs, the model boasts impressive results. Try out our free AI tools today and see what this powerful model can do! Proudly brought to you by the team behind Mangio Crepe and RMVPE.

See more

Weekly Metrics








πŸ‡ΊπŸ‡Έ English




πŸ‡ΊπŸ‡Έ English



Singing (Dry)

πŸ‡ΊπŸ‡Έ English



Singing (High)

πŸ‡ΊπŸ‡Έ English



Singing 2

πŸ‡ΊπŸ‡Έ English



Singing (Dry)

πŸ‡ΊπŸ‡Έ English



Singing (Dry, High)

πŸ‡ΊπŸ‡Έ English


Might gonna retrain for RVC V3 model.

Huggingface Link Up!

You might gonna work for you.

I think i need to find the overtraining point of this.

Because i retrain with Mangio-Crepe.

The last one that i had from Original Crepe.

yeah. mangio-crepe is better than the rvc crepe. i recommend you to set hop length into 16 if your dataset has a clean studio quality audio

i tried that in my kpop idol voice model and the result sounds like the real artist singing the song you like

I might go for 1000 epochs if i find the overtraining point.

I used Hop Length 64.

Couldn't do 16 for that

yeah the modelname.pth with epoch has included step numbers so that you won't miss it out when finding the overtraining point

maybe the dataset has noisy or reverb like?

it's ok depending on your desired preferences

Aaaaaaaah! Forgot to set the save epochs to 50!

Overtraining Point


As a result Same 350 Epochs & 10500 steps.

This means i retrain with Mangio-Crepe Extraction!

And that's it All of my RVC V2 models retrain with Mangio-Crepe Extraction.

Time to make new models!

I recommended to use the Mangio-Crepe one of this not for Original Crepe train.

Demo Sample

Audio removed in response to copyright claim.

I have to retrain for RMVPE extraction.

I think a new loss proves this one.

If 500 epochs is okay It overtrains like brrrrrrr.


The new loss is 44.

I retrain for RMVPE extraction.

Huening Bahiyyih (Kep1er) (RVC V2) 350/500 Epochs

Oh well nevermind. 1000 Epochs incoming.

Maria Ozawa RVC V2 model is coming.

I think overtrain is completed?


Huening Bahiyyih (Kep1er) (RVC V2) 350/950 Epochs

I select 950 epochs.

For a lowest loss.

RMVPE Demo Sample

Let me know if Mangio-Crepe 64 or RMVPE better.

Audio removed in response to copyright claim.

I think more models will coming up with Mangio-Crepe 64 hop and 300 epochs.

Add a comment

Selected Audio
Selected Audio