Mori Calliope (V-Tuber)

Create

Mori Calliope (V-Tuber)

RVC V2EnglishTTS / RealtimeAnimeE-celeb
Poggerking user image
Poggerking
1 year ago
👀

2.1k

👍

14

🪄

398

Description

Experience the enthralling capabilities of the Mori Calliope AI Voice Model, expertly designed using Weights' advanced RVC (Retrieval-Based Voice Conversion) technology. This model is a prime example of the cutting-edge RVC V2 framework, innovatively crafted through an intensive training process spanning 400 epochs and 36,000 steps. It captures the essence of the renowned V-Tuber, Mori Calliope, allowing you to generate incredibly lifelike AI-generated voice covers with unparalleled accuracy and a distinctly human touch. Crafted with the Ov2 Super algorithm, our AI voice model offers the perfect blend of the musical prowess and engaging persona that fans associate with the virtual talent Mori Calliope. This state-of-the-art AI Music tool is specifically optimized to create AI covers that emulate the unique tone, style, and charisma of Calliope, providing content creators the ability to produce exceptional voice content that resonates with their audience. Whether you're looking to delve into the realm of AI-powered text-to-speech applications or create mesmerizing AI covers, the Mori Calliope RVC Model from Weights is your gateway to innovation and creativity. Start leveraging this exceptional technology today and explore the endless possibilities with our free AI tools. Join us at Weights and bring your voice projects to life with our groundbreaking solutions.

Comments

Leo_Frixi user image
Leo_Frixi
1 year ago

It's kinda mid, it doesn't sound like Mori

sxndypz user image
sxndypz
1 year ago

agreed

Leo_Frixi user image
Leo_Frixi
1 year ago

Also, the test version of OV2 isn't meant for big datasets

sxndypz user image
sxndypz
1 year ago

also agreed

sxndypz user image
sxndypz
1 year ago

the dataset should be, like maximum 5-7 minutes

sxndypz user image
sxndypz
1 year ago

to use ov2

Leo_Frixi user image
Leo_Frixi
1 year ago

Froggy Simpl said it's only useful for 8-1 mins or 30 secs of audio

sxndypz user image
sxndypz
1 year ago

and if the dataset is longer than that, then i would recommend training on a regular pretrain

Leo_Frixi user image
Leo_Frixi
1 year ago

Or if it's insanely clean, use RIN

Leo_Frixi user image
Leo_Frixi
1 year ago

I hope final versions of OV2 allow any dataset length.

Poggerking user image
Poggerking
1 year ago

The date set was 30 min and thank you for the feedback for this model. I would try RIN pretraining next time.

Leo_Frixi user image
Leo_Frixi
1 year ago

No, if your dataset still had some noise, you should have used regular pretrains.

Poggerking user image
Poggerking
1 year ago

this is the data set, the audio is pretty clean for RIN i think.

Leo_Frixi user image
Leo_Frixi
1 year ago

Now i understand why your model doesn't sound like Mori.

Leo_Frixi user image
Leo_Frixi
1 year ago

Bro, don't you realize the audio is still pretty noisy? (It has static noise, room reverb, bg music and low quality voice

Leo_Frixi user image
Leo_Frixi
1 year ago

And no, if you got an dataset like that, then it's not suitable for RIN.

Poggerking user image
Poggerking
1 year ago

thank you for the help 👍

Leo_Frixi user image
Leo_Frixi
1 year ago

bruh

Leo_Frixi user image
Leo_Frixi
1 year ago

@Poggerking We suggest you to read the audio cleanup guides.

Leo_Frixi user image
Leo_Frixi
1 year ago

Your Mori model got deleted because it didn't sound even a bit like her, had low quality and static noise.

e68 user image
e68
11 months ago

Ghjgjbyhg

Add a comment

Samples

New
Classic
1. Singing
Male
English
2. Singing
Female
English
3. Singing (Dry)
Female
English
4. Singing (High)
Female
English
5. Singing 2
Male
English
6. Singing (Dry)
Male
English
7. Singing (Dry, High)
Male
English

Pitch

Selected Audio
Selected Audio