Sang-gil Lee

L0SG's activity

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

upvoted a paper about 2 months ago

PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation

Paper • 2410.01680 • Published Oct 2 • 32

updated 5 models 3 months ago

nvidia/bigvgan_v2_22khz_80band_fmax8k_256x

Audio-to-Audio • Updated Sep 5 • 5.65k

nvidia/bigvgan_v2_22khz_80band_256x

Audio-to-Audio • Updated Sep 5 • 282k • 7

nvidia/bigvgan_v2_24khz_100band_256x

Audio-to-Audio • Updated Sep 5 • 19.5k • 8

nvidia/bigvgan_v2_44khz_128band_256x

Audio-to-Audio • Updated Sep 5 • 522 • 6

nvidia/bigvgan_v2_44khz_128band_512x

Audio-to-Audio • Updated Sep 5 • 131k • 16

updated 4 models 4 months ago

nvidia/bigvgan_24khz_100band

Audio-to-Audio • Updated Jul 22 • 227 • 1

nvidia/bigvgan_base_22khz_80band

Audio-to-Audio • Updated Jul 22 • 330

nvidia/bigvgan_22khz_80band

Audio-to-Audio • Updated Jul 22 • 673

nvidia/bigvgan_base_24khz_100band

Audio-to-Audio • Updated Jul 22 • 171

updated a Space 4 months ago

Running

93

🔊

BigVGAN

updated a collection 4 months ago

BigVGAN

Collection

BigVGAN is a universal neural vocoder that generates audio waveform using mel spectrogram as input. • 11 items • Updated Oct 1 • 10

authored 3 papers 4 months ago

PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior

Paper • 2106.06406 • Published Jun 11, 2021

BigVGAN: A Universal Neural Vocoder with Large-Scale Training

Paper • 2206.04658 • Published Jun 9, 2022 • 2

Improving Text-To-Audio Models with Synthetic Captions

Paper • 2406.15487 • Published Jun 18

liked a Space 4 months ago

Running

93

🔊

BigVGAN

updated a collection 4 months ago

BigVGAN

Collection

BigVGAN is a universal neural vocoder that generates audio waveform using mel spectrogram as input. • 11 items • Updated Oct 1 • 10