Name: Ashley (From WarioWare) | AI RVC Model
Brand: Weights
Rating: 4.4 (12 reviews)

WebKit

 Discover Ashley (From WarioWare) (RVC v2) 1.9K Epoch, the latest advancement in AI Voice Models powered by Retrieval-Based Voice Conversion (RVC) technology from Weights. This cutting-edge model boasts over 1.9 thousand epochs, providing highly accurate and natural voice simulations. With its roots in the popular game franchise WarioWare, Ashley's personality shines through every conversion, making it perfect for various applications.

Equipped with a comprehensive dataset derived from Crepe hop settings, this RVC Model guarantees exceptional audio reproduction, especially when creating AI covers. Utilize the extensive 1-minute long dataset and impressive hop length of 16 for optimal results, ensuring minimal distortion while retaining authenticity.

Beyond text-to-speech capabilities, unleash your creativity using this RVC Model for generating AI music and covers across diverse genres effortlessly. Harnessing the power of artificial intelligence and fine-tuned during 1,900 training iterations, Ashley (From WarioWare) (RVC v2) 1.9K Epoch promises

Model by me Dataset by Settings: Crepe Hop Length: 16 Batch Size: 8 Epochs: 1900 Dataset Length: 1m 27s <

Ashley (From WarioWare)

Ashley (From WarioWare) (RVC v2) 1.9K Epoch

mentosandrice

I think you overtrained it, But instead you have to train 200-300 epochs if it was very great.

CrimsonZockt

You'll find that among the models I posted, those with longer datasets have less epochs because there is plenty of data without needing to go over the entire dataset many times

It's recommended to take the lowest (smoothed) value which I did. Also too low epochs makes the model sing nonsense during silences

thedoodooman

Made by me Trained on dry .flac vocals Settings: Batch Size: 1 Epochs: 1525 Dataset Length: 20m 45s - 367 clips <

Sam Smith (In the Lonely Hour Era)

Sam Smith (In the Lonely Hour Era) (RVC v2) (RMVPE) 1.5K Epochs

Made by me Trained on dry .flac vocals of SOS album Settings: Crepe Hop Length: 8 Batch Size: 8 Epochs: 440 Dataset Length: 11m 28s <

SZA (RVC v2) 440 Epoch

Model + Dataset by me Training data was sourced from the main channel + Corpse Husband clips channel Settings: Crepe Hop Length: 16 Batch Size: 8 Epochs: 360 Dataset Length: 39m 18s <

Corpse Husband

Corpse Husband (RVC v2) 360 Epoch

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 <

Jungkook (BTS)

Jungkook (BTS) (RVC v2) 1.17K Epoch

Model + Dataset by me Settings: Crepe Hop Length: 16 Batch Size: 8 Epochs: 730 Dataset Length: 9m 13s Kindly credit me if you use my model <

Ashley (From WarioWare)

Description

Samples

Saiba Momoi (Blue Archive)

Adel imam (Egyptian Actor) عادل امام (ممثل مصري)

JP Furina / Focalors CV: Inori Minase (Genshin Impact)

Ariana Grande AI

Hu Tao JP (Genshin Impact)

JENNIE of BLACKPINK [Strong Ver.]

Saiba Momoi (Blue Archive) (VA: Tokui Sora)

Hatsune Miku

SpongeBob SquarePants (Talking And Singing)

Takanashi Hoshino (from Blue Archive)

Satoru Gojo (JJK) [VA Yuichi Nakamura]

ENHYPEN Heeseung

Sunaokami Shiroko (Blue Archive)

Goku (Mario Castañeda) (Latin American Spanish) (UPDATE)

Villager (Minecraft)

Mortis [Brawl stars]

Jungkook (BTS)

Melodie - (Brawl Stars) - (English & Korean Voices)

Tendou Arisu (Blue Archive)

Kanye West