# qiuqiangkong/audioset_tagging_cnn

Repository: https://github.com/qiuqiangkong/audioset_tagging_cnn
Canonical: https://ross.abutalabs.com/products/audioset_tagging_cnn
Language: Python
License: MIT
License Family: permissive
Last push: 2024-07-25T10:16:02+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2646, "days_push": 769, "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 1772, forks 308 (observed 2026-08-28T04:05:34.221163+00:00)

## What it is
PANNs is a collection of large-scale pretrained CNN audio neural networks trained on AudioSet (5000 hours, 527 classes) for audio pattern recognition. It provides pretrained checkpoints for audio tagging and sound event detection that can be fine-tuned on downstream tasks.

## Use cases
- tag audio clips with sound classes
- detect sound events frame-wise in recordings
- extract audio embeddings for downstream tasks
- fine-tune pretrained audio models on custom classification tasks
- benchmark audio tagging models against AudioSet baselines

## When to choose
- you need state-of-the-art pretrained audio tagging or sound event detection models
- you want strong AudioSet embeddings as a base for transfer learning
- you work in Python with PyTorch and have GPU access

## When to avoid
- you need real-time low-latency audio processing on CPU
- you need a maintained production library with an API rather than research code
- your task is speech-specific (ASR/TTS) rather than general sound recognition

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, audio-processing, deep-learning
- domain: machine-learning, deep-learning
- platform: python, cross-platform
- tags: pytorch, audioset, pretrained-models, audio-tagging, sound-event-detection, panns, audio, gpu, linux

## Member repositories
- qiuqiangkong/audioset_tagging_cnn (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:34.221163+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 2026-08-30T03:25:58.039761+00:00, confidence not recorded.
  - readme: https://github.com/qiuqiangkong/audioset_tagging_cnn (fetched 2026-08-28T04:05:34.221163+00:00, sha 7dcb5179f4fe)
- Data as of 2026-08-30T08:39:29.467469+00:00.