LavaSR is a novel 50MB BWE(bandwidth extension) model along with the UL-UNAS denoiser.

Details

  • Model Size: 50mb for pytorch version.
  • Input Rate: Any from 8-48khz.
  • Output Rate: 48kHz
  • Inference Speed: 10-50x realtime on CPU and 400-4000x realtime depending on GPU.

Use cases

  • Restore low quality audio datasets
  • Enhance TTS or ASR model quality.
  • Upscale poor quality voice calls.

Benchmark Comparison

Model Speed on GPU(bs=1) Size Input range Quality
LavaSR 4000x 50MB Any from 8-48khz High
AudioSR < 1x realtime ~3gb+ ~2-16khz High
AP-BWE(previous formal fastest) < 400x realtime ~200MB+ 8khz/12khz/16khz Medium
NovaSR(previous informal fastest) <3600x realtime ~50KB+ 16khz Low

Usage

Usage instructions can be found here: https://github.com/ysharma3501/LavaSR

Final notes

The model and code are licensed under the Apache-2.0 license. See LICENSE for details.

Stars/Likes would be appreciated, thank you.

Email: yatharthsharma3501@gmail.com

Downloads last month
115
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Space using YatharthS/LavaSR 1