trained_model / config.json
raopx's picture
Training in progress, epoch 1
7e8580e verified
{
"_name_or_path": "MIT/ast-finetuned-audioset-14-14-0.443",
"architectures": [
"ASTForAudioClassification"
],
"attention_probs_dropout_prob": 0.29967735195390094,
"frequency_stride": 14,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1920741072966221,
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4",
"5": "LABEL_5",
"6": "LABEL_6",
"7": "LABEL_7",
"8": "LABEL_8",
"9": "LABEL_9",
"10": "LABEL_10",
"11": "LABEL_11",
"12": "LABEL_12",
"13": "LABEL_13",
"14": "LABEL_14"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_10": 10,
"LABEL_11": 11,
"LABEL_12": 12,
"LABEL_13": 13,
"LABEL_14": 14,
"LABEL_2": 2,
"LABEL_3": 3,
"LABEL_4": 4,
"LABEL_5": 5,
"LABEL_6": 6,
"LABEL_7": 7,
"LABEL_8": 8,
"LABEL_9": 9
},
"layer_norm_eps": 1e-12,
"max_length": 1024,
"model_type": "audio-spectrogram-transformer",
"num_attention_heads": 32,
"num_hidden_layers": 4,
"num_mel_bins": 128,
"patch_size": 16,
"problem_type": "single_label_classification",
"qkv_bias": true,
"time_stride": 14,
"torch_dtype": "float32",
"transformers_version": "4.45.1"
}