arxiv:2510.24372
Xuenan Xu PRO
wsntxxn
AI & ML interests
Text to Speech Synthesis
Text to Music Synthesis
Singing Voice Synthesis
Organizations
spaces 6
pinned
Running on Zero
Agents
5
UniFlow-Audio
👁
Generate audio from omni-modalities in a single model.
Sleeping
Agents
HoliAntiSpoof
🐢
Detect audio spoofing and get detailed analysis
Sleeping
Agents
3
STAR
🎙
Generate audio from speech input
Sleeping
Agents
4
PicoAudio2
🐨
Online inference for PicoAudio2
Runtime error
Agents
15
MM StoryAgent
📘
Generate a storytelling video from a topic and scene
Runtime error
Agents
13
Efficient Audio Captioning
🔊
Generate captions from audio files
models 12
wsntxxn/HoliAntiSpoof
Text Generation • Updated • 171
wsntxxn/UniFlow-Audio-small
0.2B • Updated • 3
wsntxxn/UniFlow-Audio-medium
0.4B • Updated • 1
wsntxxn/UniFlow-Audio-large
0.8B • Updated • 9
wsntxxn/effb2-trm-clotho-captioning
Feature Extraction • 13.6M • Updated • 11 • 1
wsntxxn/effb2-trm-audiocaps-captioning
Feature Extraction • 13.8M • Updated • 57 • 2
wsntxxn/cnn8rnn-laionclap-audiocapsv2-grounding
Audio Classification • 0.1B • Updated • 27 • 1
wsntxxn/cnn8rnn-audioset-sed
Audio Classification • 6.4M • Updated • 744 • 4
wsntxxn/cnn14rnn-tempgru-audiocaps-captioning
Feature Extraction • 0.1B • Updated • 12 • 1
wsntxxn/cnn8rnn-w2vmean-audiocaps-grounding
Audio Classification • 8.84M • Updated • 20 • 2