# kuleshov/audio-super-res

Audio super resolution using neural networks

Repository: https://github.com/kuleshov/audio-super-res
Canonical: https://ross.abutalabs.com/products/audio-super-res
Language: Python
License: MIT
License Family: permissive
Last push: 2023-10-24T23:48:19+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3460, "days_push": 1044, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1260, forks 211 (observed 2026-08-28T04:04:09.938000+00:00)

## What it is
A Python/TensorFlow implementation of neural network models for audio super resolution, upsampling low-resolution audio to higher sampling rates. It implements the Temporal FiLM and ICLR 2017 workshop models from the Kuleshov et al. papers, with scripts for preparing the VCTK speech dataset and training.

## Use cases
- upsample low-resolution audio to higher sample rates with neural networks
- enhance speech audio quality using deep learning
- reproduce audio super resolution research papers
- train a temporal FiLM model on the VCTK dataset
- increase audio sampling rate of old recordings

## When to choose
- you need neural audio upsampling and can work with TensorFlow 2.x
- you want to experiment with or extend published audio super resolution research
- you have the VCTK dataset and want a ready-made training pipeline

## When to avoid
- you need a production-ready, actively maintained audio enhancement tool
- you prefer PyTorch or modern audio ML stacks
- you want a simple CLI without preparing large training datasets

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, audio-processing, deep-learning
- domain: machine-learning, deep-learning
- platform: python
- tags: audio-super-resolution, speech-enhancement, tensorflow, signal-processing, research-code, audio, linux, macos

## Member repositories
- kuleshov/audio-super-res (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:09.938000+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:04:23.795811+00:00, confidence not recorded.
  - readme: https://github.com/kuleshov/audio-super-res (fetched 2026-08-28T04:04:09.938000+00:00, sha ce1182c06209)
- Data as of 2026-08-30T08:39:29.467469+00:00.