Sang-Hoon Lee

LeeSangHoon's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

submitted a paper to Daily Papers about 7 hours ago

WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning

Paper • 2611.12527 • Published 2 days ago • 11

upvoted a paper about 12 hours ago

Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning

Paper • 2611.12886 • Published 3 days ago • 39

New activity in LeeSangHoon/WaveGen 1 day ago

Apply for a GPU community grant: Academic project

2

#1 opened 1 day ago by

LeeSangHoon

upvoted a paper 1 day ago

WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning

Paper • 2611.12527 • Published 2 days ago • 11

published a Space 1 day ago

Running on Zero

Agents

1

WaveGen

🔊

1

WaveGen V-Spec and Flash text-to-speech on ZeroGPU

updated a Space 1 day ago

Running on Zero

Agents

1

WaveGen

🔊

1

WaveGen V-Spec and Flash text-to-speech on ZeroGPU

published a model 1 day ago

LeeSangHoon/WaveGen

Text-to-Speech • Updated 1 day ago • 2

updated a model 1 day ago

LeeSangHoon/WaveGen

Text-to-Speech • Updated 1 day ago • 2

liked a Space 9 months ago

Running

Featured

95

Parakeet STT Progressive Transcription

🎤

95

Transcribe speech to text instantly with WebGPU acceleration

liked a model 11 months ago

YatharthS/FlashSR

Audio-to-Audio • Updated Dec 26, 2025 • 67

liked a dataset 11 months ago

aanonyyy/F5I9N7A1

Viewer • Updated Oct 22, 2025 • 126k • 579 • 80

upvoted 2 papers about 2 years ago

EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer

Paper • 2409.10819 • Published Sep 17, 2024 • 18

Audio Match Cutting: Finding and Creating Matching Audio Transitions in Movies and Videos

Paper • 2408.10998 • Published Aug 20, 2024 • 9

authored 3 papers about 2 years ago

Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization

Paper • 2408.08019 • Published Aug 15, 2024 • 12

PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation

Paper • 2408.07547 • Published Aug 14, 2024 • 9

DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion

Paper • 2305.15816 • Published May 25, 2023

upvoted 2 papers about 2 years ago

PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation

Paper • 2408.07547 • Published Aug 14, 2024 • 9

Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization

Paper • 2408.08019 • Published Aug 15, 2024 • 12

liked a Space over 2 years ago

Configuration error

Agents

13

UTMOSv2

🌖

13

Generate speech quality score from audio

liked a dataset over 2 years ago

MushanW/GLOBE

Viewer • Updated May 21, 2025 • 582k • 3.99k • 32