ranvir-not-found/ast-sda_gunshot-detection

AST Gunshot Detection Model

Fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 for gunshot detection.

Model Details

• Find-tuned by: Ranabir Saha
• Fine-tuned on: Tropical forest gunshot classification training audio dataset from Automated detection of gunshots in tropical forests using convolutional neural networks (Katsis et al. 2022)
• Raw-Dataset Source: https://doi.org/10.17632/x48cwz364j.3
• Input: Precomputed log-mel spectrograms (.npy files)
• Output: Binary classification (Background/Gunshot)

Usage

from transformers import pipeline

classifier = pipeline(
    "audio-classification", 
    model="ranvir-not-found/ast-sda_gunshot-detection"
)
results = classifier("your_precomputed_spectrogram.npy")  # input must be .npy file