Any plans to release a RVQ encoder or Flow-VAE encoder to enable audio-conditioned generation?
π€ 6
1
#11 opened about 7 hours ago
by 
TheLatentSpacer
Is the model trainable?
π 1
1
#10 opened about 7 hours ago
by 
PabloFG
Without audio refrences this is useless, even more so for actual musicians
π 1
1
#9 opened about 8 hours ago
by 
FreeDiddy
Imagine if MiniMax Speech 2.8 HD (and maybe Turbo) releases on Hugging Face!
#8 opened about 9 hours ago
by 
MihaiPopa-1
rδΈηε°η,η₯θ΄ΊεεΈ
#7 opened about 10 hours ago
by 
aifeifei798
Is the song reference supported?
3
#6 opened about 10 hours ago
by 
AlperKTS
RVQ encoder
ππ 6
1
#5 opened about 10 hours ago
by 
arifqai
music quality look like suno V3.5
5
#4 opened about 11 hours ago
by 
rafiislam