boreal oar
-# that model is slightly scuffed just like any other singing models i make
this character is featured in umamusume (both the anime and game)
trained on 23:25 minutes of her singing data extracted from the game
(cleaned using anvuew's de-reverb, uvr de-echo (in some parts), some eq-ing (for the "meni shuki rush-sshu!" part), eq match, resampled to 40k)
songs used:
-
umapyoi legend
-
make debut!
-
instictive speed
-
girls' legend u
-
blow my gale
-
we are dreamers!!
-
ms. victoria
-
dramatic journey
-
tracen ondo
-
u.m.a. new world!!
-
umasugi! gourmet parade
-
uma summer
-
starting force
-
meni shuki rush-sshu!
CV: Rei Matsuzaki
pitch extraction: rmvpe
steps: 29.9k
batch size: 6
pretrain: klm 4 hfg / 40k
hf: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/hishiakebono_sing.zip
nimble hound
