
Description
The model was trained on 30 minutes of audio. 500 Epochs. It took nearly 7 hours to train but it was well worth it!
Comments
Buen modelo muy limpio ;))

Thanks! That was the intention!
Amigo, como me gustaría saber cómo hiciste este modelo, en verdad que te quedó muy bien

johancito2024, I use a website called "uvronline.app" to extract the lead vocals from a song, remove the reverb and echo, and then I use an app called "audacity" to trim out the harmonies, overlapping vocals, and spaces.
Spectacular model! Congratulations!

Which Invincible acapellas did you use?

I don't exactly remember, but it was every song with clean vocals, so around 9-10 different songs.

Thanks for the response! Great model. I made an Invincible model a while back that turned out good but yours is better.
I'd give this model an 8/10!! Really well made! ❤️
The Best Michael Jackson Vocal AI model yet. (Original Comment Deleted).
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
Users also tried
More to explore
Loading more