Skip to main content
ScriptSpeech & Audio AIv1.0

Audio Classification Setup

by Community · open-source · Last verified 2026-03-17

Configures an audio classification system using Audio Spectrogram Transformer (AST) or YAMNet fine-tuned on AudioSet, with Mel spectrogram feature extraction and batch inference. Exports per-clip predictions with top-5 class probabilities and integrates with a streaming event bus for real-time use.

https://github.com/YuanGongND/ast
C+
C+Average
Adoption: C+Quality: B+Freshness: ACitations: CEngagement: F

Specifications

License
Apache-2.0
Pricing
open-source
Capabilities
mel-spectrogram, top-k-predictions, batch-inference, streaming-support
Integrations
pytorch, torchaudio, huggingface, kafka
Use Cases
anomaly-sound-detection, wildlife-monitoring, smart-home-triggers
API Available
No
Language
python
Dependencies
torch, torchaudio, transformers, librosa, numpy
Environment
Python 3.10+
Est. Runtime
1-5 minutes
Tags
audio-classification, sound-events, ast, audioset, environmental-audio
Added
2026-03-17
Completeness
100%

Index Score

50.8
Adoption
58
Quality
78
Freshness
82
Citations
48
Engagement
0

Explore the full AI ecosystem on Agents as a Service