qiuqiangkong/audioset_tagging_cnn

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1772 stars · 308 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

machine-learning audio-processing deep-learning machine-learning deep-learning python cross-platform pytorch audioset pretrained-models audio-tagging sound-event-detection panns audio gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="qiuqiangkong/audioset_tagging_cnn")