Roca Rourin (ChromaSHIFT) (ACT2) (RVC v2) - 240 Epochs | AI HUB | Page 1

onyx basalt Feb 15, 2026, 12:18 PM

#

-# a remaster of the model i made 2 years ago

my first model trained on og pretrain after a while.

trained on (almost) 21 minutes of her speaking from the try not to laugh stream
(cleaned using hyperace v2 voc, mel denoise, anvuew room de-reverb, anvuew karaoke (in some parts), some eq, resampled to 32k)

pitch extraction: rmvpe
steps: 20.1k
batch size: 6
pretrain: original / 32k

hf: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/roca_act2.zip

#

https://tenor.com/view/roca-rourin-idol-idolen-cute-gif-11627699898984527083

Tenor

#

singing model coming soon

orchid cedar Feb 15, 2026, 6:04 PM

#

Should try making a singing model of Ironmouse

onyx basalt Feb 15, 2026, 10:37 PM

#

mind you the stream i used for data is like 1-2 years old

#

if i were to use her more recent streams, like the new outfit stream, i'd have more difficult time cleaning it because the audio's less clear than the streams from a year ago

#Roca Rourin (ChromaSHIFT) (ACT2) (RVC v2) - 240 Epochs

trained on (almost) 21 minutes of her speaking from the try not to laugh stream (cleaned using hyperace v2 voc, mel denoise, anvuew room de-reverb, anvuew karaoke (in some parts), some eq, resampled to 32k)

trained on (almost) 21 minutes of her speaking from the try not to laugh stream
(cleaned using hyperace v2 voc, mel denoise, anvuew room de-reverb, anvuew karaoke (in some parts), some eq, resampled to 32k)