BigVGAN
🔊
114
Generate high‑quality audio from your input file with BigVGAN
BigVGAN
BigVGAN is a universal neural vocoder that generates audio waveform using mel spectrogram as input.
-
-
nvidia/bigvgan_v2_44khz_128band_512x
Audio-to-Audio • Updated • 733k • 68 -
nvidia/bigvgan_v2_44khz_128band_256x
Audio-to-Audio • Updated • 358 • 7 -
nvidia/bigvgan_v2_24khz_100band_256x
Audio-to-Audio • Updated • 14.1k • 19 -
nvidia/bigvgan_v2_22khz_80band_256x
Audio-to-Audio • Updated • 1.32M • 26 -
nvidia/bigvgan_v2_22khz_80band_fmax8k_256x
Audio-to-Audio • Updated • 706 • 2 -
nvidia/bigvgan_24khz_100band
Audio-to-Audio • Updated • 814 • 4 -
nvidia/bigvgan_base_24khz_100band
Audio-to-Audio • Updated • 87 -
nvidia/bigvgan_22khz_80band
Audio-to-Audio • Updated • 273 • 1 -
nvidia/bigvgan_base_22khz_80band
Audio-to-Audio • Updated • 853 -
BigVGAN: A Universal Neural Vocoder with Large-Scale Training
Paper • 2206.04658 • Published • 4