| { | |
| "architectures": [ | |
| "ASTForAudioClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "frequency_stride": 14, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "angry", | |
| "1": "apologetic", | |
| "2": "base", | |
| "3": "calm", | |
| "4": "excited", | |
| "5": "fear", | |
| "6": "happy", | |
| "7": "sad", | |
| "8": "surprise" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "angry": 0, | |
| "apologetic": 1, | |
| "base": 2, | |
| "calm": 3, | |
| "excited": 4, | |
| "fear": 5, | |
| "happy": 6, | |
| "sad": 7, | |
| "surprise": 8 | |
| }, | |
| "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": 14, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.51.3" | |
| } | |