rookie9/PicoAudio2
Updated
•
10
Audio
-
-
PicoAudio2
🐨4Online inference for PicoAudio2
-
PicoAudio2: Temporal Controllable Text-to-Audio Generation with Natural Language Description
Paper • 2509.00683 • Published -
wsntxxn/UniFlow-Audio-large
0.8B • Updated • 22 -
wsntxxn/UniFlow-Audio-medium
0.4B • Updated • 2 -
wsntxxn/UniFlow-Audio-small
0.2B • Updated • 7 -
UniFlow-Audio
👁4Generate audio from omni-modalities in a single model.
-
UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities
Paper • 2509.24391 • Published -
Bayesian Speech synthesizers Can Learn from Multiple Teachers
Paper • 2510.24372 • Published -
marcoyang/spear-base-speech
93.3M • Updated • 4 -
marcoyang/spear-base-speech-audio
93.3M • Updated • 42 -
marcoyang/spear-large-speech
0.3B • Updated • 6 -
marcoyang/spear-large-speech-audio
0.3B • Updated • 27 -
marcoyang/spear-xlarge-speech-audio
0.6B • Updated • 530 • 1 -
SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations
Paper • 2510.25955 • Published