{ | |
"_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593", | |
"architectures": [ | |
"ASTForAudioClassification" | |
], | |
"attention_probs_dropout_prob": 0.0, | |
"frequency_stride": 10, | |
"hidden_act": "gelu", | |
"hidden_dropout_prob": 0.0, | |
"hidden_size": 768, | |
"id2label": { | |
"0": "anger", | |
"1": "disgust", | |
"2": "enthusiasm", | |
"3": "fear", | |
"4": "happiness", | |
"5": "neutral", | |
"6": "sadness" | |
}, | |
"initializer_range": 0.02, | |
"intermediate_size": 3072, | |
"label2id": { | |
"anger": 0, | |
"disgust": 1, | |
"enthusiasm": 2, | |
"fear": 3, | |
"happiness": 4, | |
"neutral": 5, | |
"sadness": 6 | |
}, | |
"layer_norm_eps": 1e-12, | |
"max_length": 1024, | |
"model_type": "audio-spectrogram-transformer", | |
"num_attention_heads": 12, | |
"num_hidden_layers": 12, | |
"num_mel_bins": 128, | |
"patch_size": 16, | |
"problem_type": "single_label_classification", | |
"qkv_bias": true, | |
"time_stride": 10, | |
"torch_dtype": "float32", | |
"transformers_version": "4.27.4" | |
} | |