# despoisj/DeepAudioClassification

Finding the genre of a song with Deep Learning

Repository: https://github.com/despoisj/DeepAudioClassification
Canonical: https://ross.abutalabs.com/products/deepaudioclassification
Homepage: https://medium.com/@juliendespois/finding-the-genre-of-a-song-with-deep-learning-da8f59a61194#.yhemoyql0
Language: Python
License Family: other
Topics: deep-learning, machine-learning, neural-networks, artificial-intelligence, music
Last push: 2021-07-26T19:31:50+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": 3566, "days_push": 1864, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1114, forks 217 (observed 2026-08-28T04:03:38.180768+00:00)

## What it is
A Python pipeline that builds a dataset from a personal music library and trains a deep learning model to classify songs by genre. It accompanies a Medium article and slices MP3s into segments for training a TensorFlow/TFLearn classifier.

## Use cases
- classify music files by genre with deep learning
- build a dataset from my own mp3 library
- learn audio classification with spectrograms
- fill in missing genre tags on songs
- example of training a CNN on audio slices

## When to choose
- learning how audio classification pipelines work
- following along with the accompanying Medium tutorial
- experimenting with genre classification on your own music collection

## When to avoid
- production music tagging at scale
- projects needing maintained dependencies or a license
- modern TensorFlow versions since it relies on deprecated tflearn

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: deep-learning, machine-learning, audio-processing, data-science
- domain: machine-learning, deep-learning, audio
- platform: python, cross-platform
- tags: music-genre-classification, tensorflow, tflearn, audio-classification, tutorial, spectrogram, audio

## Member repositories
- despoisj/DeepAudioClassification (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:38.180768+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 2026-08-30T06:42:16.734766+00:00, confidence not recorded.
  - readme: https://github.com/despoisj/DeepAudioClassification (fetched 2026-08-28T04:03:38.180768+00:00, sha 1230dbe84265)
- Data as of 2026-08-30T08:39:29.467469+00:00.