| { | |
| "model_type": "audio-spectrogram-transformer", | |
| "framework": "PyTorch + LightGBM", | |
| "audio_processing_params": { | |
| "sample_rate": 12000, | |
| "duration": 3, | |
| "padding_method": "reflect" | |
| }, | |
| "features_params": { | |
| "n_fft": 512, | |
| "hop_length": 256, | |
| "pad": 0, | |
| "power": 2, | |
| "pad_mode": "reflect", | |
| "f_min": 70, | |
| "f_max": 1525, | |
| "fc_min": 0.05, | |
| "fc_max": 0.8 | |
| }, | |
| "lgbm_params": { | |
| "objective": "binary", | |
| "metric": "binary_logloss", | |
| "boosting_type": "gbdt", | |
| "learning_rate": 0.1, | |
| "num_leaves": 75, | |
| "max_depth": -1, | |
| "feature_fraction": 0.8, | |
| "bagging_fraction": 0.8, | |
| "bagging_freq": 5, | |
| "verbosity": -1 | |
| } | |
| } |