pipeline_tag: audio-to-audio
Models creaded with and in the use in the Vul So-Vits-SVC 4.0 UI.
_List of models:
----Pony:
CakeMrs_70
Derpy_100000
Spike_45000
TreeHugger_69k
ddm_DaringDo_100k (+ Lighting Dust and Moondancer)
djPon3_Dash_Mix_85000
----Non-Pony:
DRD_60000
Dagoth_Ur_50k
Dagoth_Ur_80k
Glados_50k
Gwenpool_50000 (multilingual)
NamelessHero_eng
Saul_Goodman_80000
TF2_SaxtonHale_100k
TF2_demoman_75k
TF2_engineer_60k
TF2_heavy_100k
TF2_medic_100k
TF2_scout_60k
TF2_sniper_60k
TF2_soldier_60k
TF2_spy_60k
g1_Diego_PL_60000
_List of datasets:
TF2_SaxtonHale_100k, TF2_demoman_75k, TF2_engineer_60k, TF2_heavy_100k, TF2_medic_100k, TF2_scout_60k, TF2_sniper_60k, TF2_soldier_60k, TF2_spy_60k
DRD_MLP
Daring_Do_multiple
DerpyWavExpanded
djPon3_Dash_Mix_(audio_dataset) (OLD, im working on making update on this)
Dagoth Ur