ARespiratory audio classification model
This model classifies respiratory audio recordings from the ICBHI 2017 Challenge dataset into crackles, wheezes, both, or none (multi-label classification). It utilizes the AST encoder (MIT/ast-finetuned-audioset-14-14-0.443) with a lightweight classification head.
The model has been pushed to the Hub using the PyTorchModelHubMixin integration.
Dataset
- Source: ICBHI 2017 Challenge
Performance metrics
| Label | F1 | Precision | Recall | AUC |
|---|---|---|---|---|
| Crackle | 0.6756 | 0.6147 | 0.7500 | 0.7033 |
| Wheeze | 0.4853 | 0.6565 | 0.3849 | 0.8031 |
| Macro Avg | 0.5805 | 0.6356 | 0.5674 | 0.7532 |
Usage
Run inference using s05_inference.py.
Ensure you install the necessary dependencies. For setup instructions, please see the documentation.
Notes
For additional details, check the documentation notes.
Contact
For any questions or further information, feel free to reach out via email: fabiocat@mit.edu.
- Downloads last month
- 51