Name: Utatane Nasa (Phase Connect / VTuber) | AI RVC Model
Brand: Weights
Rating: 4.6 (7 reviews)

Discover the innovative realm of AI music with our latest RVC Model, the "Utatane Nasa (Phase Connect / VTuber) (RVC v2) – 550 Epochs", meticulously crafted to encapsulate the essence of the iconic virtual YouTuber, Utatane Nasa of Phase Connect. This cutting-edge model has undergone intensive training locally with over 550 epochs, ensuring a nuanced and faithful recreation of her unique vocal timbre. Leveraging just 15 minutes of high-quality audio extracted using advanced pitch extraction techniques, our AI has mastered the subtle intonations and inflections characteristic of Nasa's speaking style, perfect for creating AI covers with remarkable accuracy.

Pushing the boundaries of AI voice generation, the "Utatane Nasa" RVC model operates on the latest regular v2 configuration and boasts a precise batch size of 6 for optimal neural network training. The result is a robust and dynamic voice model compatible with RVC v2 architecture, fueling the next wave of personalized voice content in the field of AI entertainment.

Bring your musical projects to life by leveraging the voice of Utatane Nasa. With Weights' free AI tools, you can effortlessly create AI covers or engage in text-to-speech applications, giving your content a distinctive edge that captivates your audience. Dive into the future of AI music creation with Weights and experience the unparalleled fidelity of our Utatane Nasa RVC Model today. Embrace the innovative fusion of AI and music – start crafting your AI-generated covers and narratives now.

this is the first ever model i've trained locally. trained on 15 minutes of her speaking from the stream pitch extraction: rmvpe steps: 20.6 - 20.7k batch size: 6 pretrain: regular v2 / 32k huggingface:

Utatane Nasa (Phase Connect / VTuber)

Utatane Nasa (Phase Connect / VTuber) (RVC v2) - 550 Epochs

sxndypz

Utatane Nasa (Phase Connect / VTuber) (RVC v2) - 440 Epochs

for weights users: it's actually trained in 440 epochs mb

next model is pdob going to be meimei himari

if anyone doesn't know who she is she's a jp indie(?) vtuber that has a tts voicebank in a program called voicevox

new model of koyori after a whole year? crazy. trained on (almost) 17 minutes of data from her recent streams. (rx spectral denoise de-click de-reverb) pitch extraction: rmvpe steps: 18.8k/18.9k batch size: 7 pretrain: klm 4.1 / 32k huggingface:

Hakui Koyori (hololive / holoX)

Hakui Koyori (hololive / holoX) (RVC v2) - 350 Epochs

3rd idolen vtuber model lfg trained on (almost) 13 minutes of audio data from her recent watchalong stream (rx de-click de-noise(?) uvr de-reverb) pitch extraction: rmvpe steps: 18.4k batch size: 7 pretrain: klm 4.1 / 32k huggingface:

Shabel Tonya (idol-EN)

Shabel Tonya (idol-EN) (RVC v2) - 450 Epochs

first model that is not a vtuber/anime character related yippee trained on 1 minute of data from the yapdollar tiktok/short. (mel roformer + resemble enhance) pitch extraction: rmvpe steps: ???k (don't know trained this when i was away from home) batch size: 2 pretrain: klm 4.1 / 32k huggingface:

Yapdollar

Yapdollar (RVC v2) - 700 Epochs

another phase connect model yipiiii woohoo trained on roughly 16 minutes of data from her stream (xminus mel roformer + uvr de-reverb (the new x-minus one not the de-echo-de-reverb one) + de-click) pitch extraction: rmvpe steps: 14.9k/15k batch size: 7 pretrain: klm 4.1 / 32k huggingface:

Ayase Yuu (Phase Connect)

Ayase Yuu (Phase Connect) (RVC v2) - 320 Epochs

awawawawawawawawawaawawawawaaw 2.0: the grand return sounds clearer than the jelly model i've made earlier trained on 17 minutes of data from her malware stream (xminus mel roformer + uvr de-reverb (the new x-minus one not the de-echo-de-reverb one) rx11 de-plosive + de-click) pitch extraction: rmvpe steps: 15.5k batch size: 7 pretrain: klm 4.1 / 32k huggingface:

Jelly Hoshiumi (ACT2) (Phase Connect)

Jelly Hoshiumi (ACT2) (Phase Connect) (RVC v2) - 310 Epochs

Origin: HoloMyth (Hololive English) minutes and 46 seconds of Gura talking Batch size per GPU used during training: 8 Image made courtesy of Nachoneko 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.

Utatane Nasa (Phase Connect / VTuber)

Description

Add a comment

Gawr Gura

Saiba Momoi (Blue Archive)

Villager (Minecraft)

Sas (Counter-strike global offensive)

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

Fang [Brawl Stars]

Jay (ENHYPEN)

Satoru Gojo (JJK) [VA Yuichi Nakamura]

Mortis [Brawl stars]

Jungkook (BTS)

ENHYPEN Heeseung

Sonic The Hedgehog [Roger Craig Smith]

Ariana Grande AI

Takanashi Hoshino (from Blue Archive)

Surge (brawl Stars)

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

SpongeBob SquarePants (Talking And Singing)

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

Miss Circle (Fundamental Paper Education)

CaseOh

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