universr-audio

UniverSR - General Audio (Flagship)

Vocoder-free audio super-resolution model that upsamples 8/12/16/24 kHz → 48 kHz audio using flow matching in the complex STFT domain. Trained on speech, music, and sound effects.

This is the recommended model for general use. For speech-only evaluation (e.g. VCTK benchmark), see universr-speech.

Paper: arXiv:2510.00771 | Demo: woongzip1.github.io/universr-demo | Code: github.com/woongzip1/UniverSR

Usage

import torchaudio
from universr import UniverSR

model = UniverSR.from_pretrained("woongzip1/universr-audio", device="cuda")
output = model.enhance("low_res.wav", input_sr=8000)
torchaudio.save("output_48k.wav", output.cpu(), 48000)

Citation

@inproceedings{choi2026universr,
  title     = {{UniverSR}: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow Matching},
  author    = {Choi, Woongjib and Lee, Sangmin and Lim, Hyungseob and Kang, Hong-Goo},
  booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
  year      = {2026}
}