LHugueny singing
ArtistRVC v2E-CelebEnglish

📣

From the creator

"i decided i would remake the lhugueny rvc v2 model cause i've gotten alot better at rvc as of recently and i think the original rvc model i made of him was a bit shit. i also made a 300 epoch version but it sounds exactly the same if not a little worse than the 150 epoch version so i'll release this instead of the 300 epoch version if yall want me to upload the 300 epoch one i'll gladly do it tho"

Description

Introducing the enhanced LHugueny singing model by RVC v2, powered by 400 epochs and 40k data points. This advanced AI voice model captures improved audio quality and authenticity compared to its predecessor. Ideal for creating AI covers and text-to-speech applications, the model generates human-like vocals simulating the original singer. With high-quality outputs similar to professional productions, users can explore various scenarios like karaoke sessions, virtual concerts, or personalized messages effortlessly. Try out our free AI tools today and experience the power of AI music!

See more

Weekly Metrics

Samples

New
Classic
TTS

Pitch

0

1

Male

Singing

🇺🇸 English

2

Female

Singing

🇺🇸 English

3

Female

Singing (Dry)

🇺🇸 English

4

Female

Singing (High)

🇺🇸 English

5

Male

Singing 2

🇺🇸 English

6

Male

Singing (Dry)

🇺🇸 English

7

Male

Singing (Dry, High)

🇺🇸 English

Comments

btw you formatted it wrong

you need to put the pth and the index in a zip file and upload it to huggingface as a model

like this

also its undertrained

I trained it to 300 epochs and it sounded exactly the same

If not a little worse

The dataset is 35 minutes

you totally undertrained it

Can u help me make it better

use the 300 epoch

just train it more lol

It sounds worse tho

use the graph and save every 50 epochs

I saved every 50

send me a sample with it

Go to the rapping model and listen to the kanye.wav file

oh alr

WELL DUH ITS 100 EPOCHS

not 300

its 100 epochs not 300.

The rapping model is a different model

For the and I wonder if you know how it feels part I used the 300 epoch lhugueny model

And for kanyes vocals I used the rapping model

damn alr

it sounds a bit better than this tho

listen to this

I’ll go on my pc now and upload the 300 epoch version

LHugueny singing (RVC v2 400 epochs 40k mangio crepe)

not enough autotune

great yapping comments

Whoa-oh-oh-oh-oh-oh-oh-oh-oh-oh Story of Undertale

I don't notice anything I think StakenS is high.

Add a comment

Post