MODEL LINK: https://huggingface.co/joebamnasoda69/CheckardsArrVeeSeeStuff/resolve/main/RalseiUpdated.zip?download=true
Trained by me. No credit needed.

Yep, we're so back and loving the new pretrains.
Now, before you say "Oh, but Ralsei doesn't even have an actual canon voice, the only sound he makes is a-a-a-a-a-a" or something like that, let me tell you how I made the dataset.

The dataset created by taking his little dialogue noise, stretching it out, EQ-ing it through heck and back to make vowel sounds, splicing it with some of the in-game sfx to make consonants, making a model out of it, generating some pretty decent audio with said model, cherry-picking the audio I generated and adding that audio to the dataset, and making a model out of that dataset to *slightly* improve pronunciation. (Neither Elevenlabs nor TortoiseTTS were used.)

EXTRA NOTES: Index file kinda sucks, so I recommend turning the index feature ratio on the lower end OR using a different index file entirely.

Additional Details:

Tags: No tags available

Download Link: https://huggingface.co/joebamnasoda69/CheckardsArrVeeSeeStuff/resolve/main/RalseiUpdated.zip?download=true Hosted on Hugging Face