Jungkook (BTS)

Staff pick

ArtistRVC v2Korean

๐Ÿ“ฃ

From the creator

"Model + Dataset by me This is an update to my previous Jungkook RVC v1 model +Much higher pitch accuracy and realism +Used tensorboard to select model with minimal loss before overtraining Settings: Crepe Hop Length: 16 Batch Size: 8 Epochs: 1175 Dataset Length: 6m 46s Kindly credit me if you use my model"

Description

Introducing the Jungkook (BTS) (RVC v2) 1.17K Epoch - the latest advancement in AI voice modeling by Weights! This cutting-edge model has been trained using Retrieval-Based Voice Conversion (RVC) technology, allowing it to accurately replicate the charming and iconic vocals of BTS member, Jungkook. With enhanced pitch accuracy compared to its predecessor, version 1, this upgraded model provides a more authentic listening experience. Our Jungkook (BTS) (RVC v2) 1.17K Epoch model opens new doors for creators seeking to generate AI music covers or experiment with text-to-speech applications. As part of our mission at Weights to provide innovative AI solutions, we're excited to offer you access to these powerful tools โ€“ completely free of charge. Dive into limitless possibilities and start creating your own AI covers today, all while harnessing the power of our advanced RVC Model. Join us in pushing the boundaries of artificial intelligence and take advantage of our top-notch, free AI tools now!

See more

Weekly Metrics

Samples

New
Classic
TTS

Pitch

0

1

Male

Singing

๐Ÿ‡บ๐Ÿ‡ธ English

2

Female

Singing

๐Ÿ‡บ๐Ÿ‡ธ English

3

Female

Singing (Dry)

๐Ÿ‡บ๐Ÿ‡ธ English

4

Female

Singing (High)

๐Ÿ‡บ๐Ÿ‡ธ English

5

Male

Singing 2

๐Ÿ‡บ๐Ÿ‡ธ English

6

Male

Singing (Dry)

๐Ÿ‡บ๐Ÿ‡ธ English

7

Male

Singing (Dry, High)

๐Ÿ‡บ๐Ÿ‡ธ English

Comments

Samples:

Audio removed in response to copyright claim.

Audio removed in response to copyright claim.

Audio removed in response to copyright claim.

Woah there This is definitely highly overtrained RVC v2 models with small datasets only need less than 200 epochs for good results

I checked the tensorboard loss/g/total checks out

๐Ÿ‘

Here is the graph the model is right before the 20k mark

image.png

Pretty sure you should have stopped at 12k

I could but the loss wouldn't be as low. I basically let it train for a long time and pick whatever point is lowest when I come back to the PC

not good. too soft

Add a comment

Post

Privacy

โ€ข

Terms

โ€ข

DMCA