Description
VA: Ratana Trained on 2hr 3m of in game voice lines. 300 epoch Model: 200 epoch Model: This was the second try for Yae because the first one had some bad audio. *Thank Bingle for the scripts used in this model*
Comments
Took 24hrs on batch 8 on a rtx 3060
Raiden x Yae
2hrs of dataset that's some serious dedication!
Only take about 20 hours of waiting for it to train 2hr dataset
Power bill 📈
I would ask bingle as they made a complete script
I used their decryption script with some of my own modifications for other stuff
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