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
.
import torchaudio
from universr import UniverSR
model = UniverSR.from_pretrained("woongzip/universr-audio", device="cuda")
output = model.enhance("low_res.wav", input_sr=16000)
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}
}
Runs of woongzip1 universr-audio on huggingface.co
5.9K
Total runs
-229
24-hour runs
-1.0K
3-day runs
-1.7K
7-day runs
-2.1K
30-day runs
More Information About universr-audio huggingface.co Model
universr-audio huggingface.co is an AI model on huggingface.co that provides universr-audio's model effect (), which can be used instantly with this woongzip1 universr-audio model. huggingface.co supports a free trial of the universr-audio model, and also provides paid use of the universr-audio. Support call universr-audio model through api, including Node.js, Python, http.
universr-audio huggingface.co is an online trial and call api platform, which integrates universr-audio's modeling effects, including api services, and provides a free online trial of universr-audio, you can try universr-audio online for free by clicking the link below.
woongzip1 universr-audio online free url in huggingface.co:
universr-audio is an open source model from GitHub that offers a free installation service, and any user can find universr-audio on GitHub to install. At the same time, huggingface.co provides the effect of universr-audio install, users can directly use universr-audio installed effect in huggingface.co for debugging and trial. It also supports api for free installation.