| { | |
| "_name_or_path": "ntu-spml/distilhubert", | |
| "activation_dropout": 0.1, | |
| "apply_spec_augment": false, | |
| "architectures": [ | |
| "HubertForSequenceClassification" | |
| ], | |
| "attention_dropout": 0.1, | |
| "bos_token_id": 1, | |
| "classifier_proj_size": 256, | |
| "conv_bias": false, | |
| "conv_dim": [ | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512 | |
| ], | |
| "conv_kernel": [ | |
| 10, | |
| 3, | |
| 3, | |
| 3, | |
| 3, | |
| 2, | |
| 2 | |
| ], | |
| "conv_stride": [ | |
| 5, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2 | |
| ], | |
| "ctc_loss_reduction": "sum", | |
| "ctc_zero_infinity": false, | |
| "do_stable_layer_norm": false, | |
| "eos_token_id": 2, | |
| "feat_extract_activation": "gelu", | |
| "feat_extract_norm": "group", | |
| "feat_proj_dropout": 0.0, | |
| "feat_proj_layer_norm": false, | |
| "final_dropout": 0.0, | |
| "hidden_act": "gelu", | |
| "hidden_dropout": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "Soundscape", | |
| "1": "Drone", | |
| "2": "Chop", | |
| "3": "Sub", | |
| "4": "Glitch", | |
| "5": "Impact", | |
| "6": "Stab (attacck resonance)", | |
| "7": "Synthesis", | |
| "8": "Vocal", | |
| "9": "Scratch", | |
| "10": "Crackle", | |
| "11": "Noise", | |
| "12": "Textural", | |
| "13": "Instrumental", | |
| "14": "Chirp", | |
| "15": "Percussive", | |
| "16": "Honk", | |
| "17": "Choral" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "Chirp": 14, | |
| "Chop": 2, | |
| "Choral": 17, | |
| "Crackle": 10, | |
| "Drone": 1, | |
| "Glitch": 4, | |
| "Honk": 16, | |
| "Impact": 5, | |
| "Instrumental": 13, | |
| "Noise": 11, | |
| "Percussive": 15, | |
| "Scratch": 9, | |
| "Soundscape": 0, | |
| "Stab (attacck resonance)": 6, | |
| "Sub": 3, | |
| "Synthesis": 7, | |
| "Textural": 12, | |
| "Vocal": 8 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "layerdrop": 0.0, | |
| "mask_feature_length": 10, | |
| "mask_feature_min_masks": 0, | |
| "mask_feature_prob": 0.0, | |
| "mask_time_length": 10, | |
| "mask_time_min_masks": 2, | |
| "mask_time_prob": 0.05, | |
| "model_type": "hubert", | |
| "num_attention_heads": 12, | |
| "num_conv_pos_embedding_groups": 16, | |
| "num_conv_pos_embeddings": 128, | |
| "num_feat_extract_layers": 7, | |
| "num_hidden_layers": 2, | |
| "output_hidden_states": true, | |
| "pad_token_id": 0, | |
| "problem_type": "multi_label_classification", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.37.2", | |
| "use_weighted_layer_sum": false, | |
| "vocab_size": 32 | |
| } | |