# ronibandini/reggaetonBeGone

Detects reggaeton genre with Machine Learning and sends packets to disable BT speakers (hopefully)

Repository: https://github.com/ronibandini/reggaetonBeGone
Canonical: https://ross.abutalabs.com/products/reggaetonbegone
Homepage: https://bandini.medium.com/reggaeton-be-gone-6fa55f46a9d7
Language: Python
License: MIT
License Family: permissive
Topics: bluetooth, ddos, machine-learning, music, python, reggaeton
Last push: 2026-08-22T20:54:19+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 66
- inputs: {"age_days": 925, "days_push": 11, "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 1005, forks 118 (observed 2026-09-03T02:15:17.465169+00:00)

## What it is
A Raspberry Pi-based edge machine learning device that continuously samples ambient audio and uses an Edge Impulse audio classification model to detect reggaeton music. When detection confidence exceeds a threshold, it triggers a Bluetooth test routine against a configured nearby speaker, inspired by TV-B-Gone.

## Use cases
- detect reggaeton music playing nearby with machine learning
- classify music genre from ambient audio on a Raspberry Pi
- run Edge Impulse audio inference on edge hardware
- build a TV-B-Gone style device for Bluetooth speakers
- experiment with Bluetooth routines triggered by audio classification
- display ML inference confidence on an OLED screen

## When to choose
- you want a fun maker project combining edge ML, Raspberry Pi, and Bluetooth experimentation
- you need local audio genre classification on ARM hardware without cloud services
- you want a hardware reference for Edge Impulse .eim models with OLED and button peripherals

## When to avoid
- you need a reliable or legal way to disable other people's Bluetooth speakers
- you need production-grade audio classification or general music genre recognition
- you want a portable solution without a Raspberry Pi (the author's Pocket Gone is simpler)
- you need supported, maintained software rather than an experimental novelty build

## Facets
- artifact type: application
- maturity: experimental
- function: machine-learning, audio-processing, speech-recognition, security
- domain: machine-learning, hardware, developer-tools
- platform: python, embedded
- tags: edge-ml, raspberry-pi, edge-impulse, bluetooth, music-genre-classification, audio-classification, oled-display, novelty-project, audio, linux

## Member repositories
- ronibandini/reggaetonBeGone (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:17.465169+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 2026-08-30T07:13:46.664918+00:00, confidence not recorded.
  - readme: https://github.com/ronibandini/reggaetonBeGone (fetched 2026-09-03T02:15:17.465169+00:00, sha 24f83cf57377)
  - homepage: https://bandini.medium.com/reggaeton-be-gone-6fa55f46a9d7 (fetched 2026-08-29T13:13:29.792172+00:00, sha 4a164dd8d69f)
- Data as of 2026-08-30T08:39:29.467469+00:00.