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
It's kinda mid it doesn't sound like Mori
agreed
Also the test version of OV2 isn't meant for big datasets
also agreed
the dataset should be like maximum 5-7 minutes
to use ov2
Froggy Simpl said it's only useful for 8-1 mins or 30 secs of audio
and if the dataset is longer than that then i would recommend training on a regular pretrain
Or if it's insanely clean use RIN
I hope final versions of OV2 allow any dataset length.
The date set was 30 min and thank you for the feedback for this model. I would try RIN pretraining next time.
No if your dataset still had some noise you should have used regular pretrains.
this is the data set the audio is pretty clean for RIN i think.
Now i understand why your model doesn't sound like Mori.
Bro don't you realize the audio is still pretty noisy? (It has static noise room reverb bg music and low quality voice
And no if you got an dataset like that then it's not suitable for RIN.
thank you for the help π
bruh
@Poggerking We suggest you to read the audio cleanup guides.
Your Mori model got deleted because it didn't sound even a bit like her had low quality and static noise.
Ghjgjbyhg
Add a comment
Samples
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
Weekly Metrics
Users also tried
Collections with this model
More to explore
Loading more