H2oSakana (CEO of Phase Connect)

πŸ“£

From the creator

"woohoo the ceo of phase connect ai model yeah baby we're rollin trained on 11 and a half minutes of him speaking from jelly's ama stream pitch extraction: rmvpe steps: 18k(?) batch size: 7 pretrain: regular v2 / 32k huggingface:"

Description

Introducing the "H2oSakana (CEO of Phase Connect) (RVC v2) - 520 Epochs" AI Voice Model from Weights. This sophisticated RVC (Retrieval-Based Voice Conversion) Model embodies the unparalleled essence of the CEO of Phase Connect, trained meticulously on over 11 minutes of his eloquent speech from Jelly's AMA stream. This model, optimized after a staggering 520 epochs, employs advanced pitch extraction techniques like RMVPE and utilizes a batch size of 7 for efficient training. Adopting the power and precision of the regular V2, the model also integrates the innovative capabilities of a 32k Huggingface. Harness your creative prowess in AI music and create persuasive AI covers that adroitly mimic the CEO’s distinctive voice. Explore the futuristic scope of Text-to-Speech conversion with our leading-edge free AI tools at Weights. So why wait? Embrace the future of AI and create your unique AI Covers today!

See more

Weekly Metrics

Samples

New
Classic

Pitch

0

1

Male

Singing

πŸ‡ΊπŸ‡Έ English

2

Female

Singing

πŸ‡ΊπŸ‡Έ English

3

Female

Singing (Dry)

πŸ‡ΊπŸ‡Έ English

4

Female

Singing (High)

πŸ‡ΊπŸ‡Έ English

5

Male

Singing 2

πŸ‡ΊπŸ‡Έ English

6

Male

Singing (Dry)

πŸ‡ΊπŸ‡Έ English

7

Male

Singing (Dry, High)

πŸ‡ΊπŸ‡Έ English

Comments

samples soon

i think

the sample's a bit broken because of the acapella but this will do.

Audio removed in response to copyright claim.

In some parts it sounds authentic but in some other parts it got artifacting.

the dataset's a bit scuffed

🐟

Add a comment

Post

Privacy

β€’

Terms

β€’

DMCA