Name: Comet-chan (Suisei Hoshimachi) | AI RVC Model
Brand: Weights
Rating: 4.6 (8 reviews)

 Introducing Comet-chan, the latest addition to our advanced AI Voice Models lineup at Weights! Based on the beloved virtual YouTuber Suisei Hoshimachi, Comet-chan brings her unique charm and personality to life using cutting-edge Retrieval-Based Voice Conversion (RVC) technology. With just minutes and 32 seconds of Suisei's original voice samples, we have created an incredibly accurate and expressive AI Model that captures her distinct vocal patterns and inflections.

Our Comet-chan RVC Model enables you to generate entirely new dialogues and even create AI covers of your favorite songs sung by Suisei herself! Ideal for musicians, animators, content creators, and anyone interested in exploring the exciting possibilities offered by artificial intelligence and synthetic media, Comet-chan allows you to push creative boundaries like never before.

Transform text into lifelike speech or generate mesmerizing AI music – all for free using our powerful yet user-friendly suite of Weights AI Tools! Start crafting immersive stories, engaging presentations, and innovative musical creations today with Comet-chan leading the way. Join us now and experience the future of entertainment

Origin: Hololive minutes and 32 seconds of Suisei Hoshimachi speaking as "Comet-chan" from her 2023 April Fools' stream Batch size per GPU used during training: 8 Image made courtesy of DK Sotti Credit would be much appreciated if you used this model Discord: or YouTube: @AIDontEvenKnow-cd8qe You are solely responsible with what you create with this model so use wisely.

Comet-chan (Suisei Hoshimachi)

AIDontEvenKnow

This audio sample was inferred on the Aesthetic RVC Inferrence Hugging Face Space by r3gm using the RMVPE+ pitch extraction algorithm with "Split Audio" enabled on a minimum value of 82 Hz and a maximum value of 330 Hz.

Comet-chan (Suisei Hoshimachi) [RVC v2] [RMVPE] 740 Epochs 18500 Steps

Amelia Walasek

Origin: Rock music Trained on: 48 seconds of Meissner singing: 26 seconds from *Dangerous Games* 22 seconds from *Windows to Light* Save frequency: 10 epochs Log interval: 100 steps Batch size used during training: 3 Sample rate: 32k Image made courtesy of unknown photographer Credit would be much appreciated if you used this model Discord: @AIDontEvenKnow or YouTube: @AIDontEvenKnow-cd8qe You are solely responsible with what you create with this model so use wisely.

Stan Meissner

Stan Meissner [RVC v2] [RMVPE] 210 Epochs 2100 Steps

Origin: Progressive rock music (most notably: King Crimson, U.K. and Asia) Epochs: 670 Steps: 6700 Trained on: 02 minutes and 32 seconds of Wetton singing songs by King Crimson and U.K. from live recordings: * 17 seconds from Starless and Bible Black by King Crimson * 49 seconds from USA by King Crimson * 01 minute and 24 seconds from Night After Night by U.K. Save frequency: 10 epochs Log interval: 100 steps Batch size used during training: 10 Sample rate: 32k Image made courtesy of Mike Inns Credit would be much appreciated if you used this model Discord: @AIDontEvenKnow or YouTube: @AIDontEvenKnow-cd8qe You are solely responsible with what you create with this model so use wisely.

John Wetton

Origin: HoloMyth (Hololive English) Epochs: 455 Steps: 15925 Trained on: 59 minutes and 55 seconds of Kiara talking Save frequency: 5 epochs Log interval: 175 steps Batch size used during training: 32 Sample rate: 32k Image made courtesy of Kurohoshi (@96hoshii_0317) Credit would be much appreciated if you used this model Discord: @RigidSpinner or YouTube: @AIDontEvenKnow-cd8qe You are solely responsible with what you create with this model so use wisely.

Kiara Takanashi

Origin: Chicago Epochs: 640 Steps: 3200 Trained on: 01 minute and 42 seconds of Lamm singing songs from his solo career and non-Chicago materials: * 46 seconds from Life is Good in My Neighborhood * 46 seconds from In My Head * 04 seconds from Like a Brother by Beckley-Lamm-Wilson * 00 seconds from The Bossa Project * 04 seconds from Robert Lamm Songs: JVE Remixes Save frequency: 40 epochs Log interval: 200 steps Batch size used during training: 8 Sample rate: 32k Image made courtesy of Robert Lamm (note: this image was edited) Credit would be much appreciated if you used this model Discord: @RigidSpinner or YouTube: @AIDontEvenKnow-cd8qe You are solely responsible with what you create with this model so use wisely.

Robert Lamm [1993-2012 Era]

Origin: Voice actress (seiyuu) (most notably: Akame (Akame ga Kill!) Aqua (KonoSuba) and Kasumi Yoshizawa (Persona 5 Royal)) and TrySail Epochs: 780 Steps: 7800 Trained on: 08 minutes and 35 seconds of Amamiya singing and talking from Paint It Sky (2020) Save frequency: 20 epochs Log interval: 200 steps Batch size used during training: 16 Sample rate: 32k Image made courtesy of the Ministry of Internal Affairs and Communications (note: this image was edited) Credit would be much appreciated if you used this model Discord: @RigidSpinner or YouTube: @AIDontEvenKnow-cd8qe You are solely responsible with what you create with this model so use wisely.

Comet-chan (Suisei Hoshimachi)

Description

Add a comment

Saiba Momoi (Blue Archive)

Jungkook (BTS)

ENHYPEN Heeseung

Sas (Counter-strike global offensive)

Fang [Brawl Stars]

Edgar [Brawl Stars]

Cordelius Brawl Stars

Baldi (Baldi's Basics in Education and Learning)

Mortis [Brawl stars]

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

Sonic The Hedgehog [Roger Craig Smith]

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

Surge (brawl Stars)

Janet (Brawl Stars)

Hu Tao JP (Genshin Impact)

Sunghoon ENHYPEN

Villager (Minecraft)

FIXED HATSUNE MIKU V3 - VOCALOID [SCROLL DOWN FOR LINK]

Ariana Grande AI

Satoru Gojo (JJK) [VA Yuichi Nakamura]

Jay (ENHYPEN)

Tendou Arisu (Blue Archive)

Donald Trump

SpongeBob SquarePants (Talking And Singing)

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

Takanashi Hoshino (from Blue Archive)

CaseOh

JENNIE of BLACKPINK [Strong Ver.]

Sunaokami Shiroko (Blue Archive)

Alastor (Hazbin Hotel/English)