| { |
| "activation_dropout": 0.0, |
| "activation_fn": "gelu", |
| "apply_mask": null, |
| "architectures": [ |
| "AVHubertModel" |
| ], |
| "attention_dropout": 0.1, |
| "audio_dropout": 0.5, |
| "audio_feat_dim": 104, |
| "auto_map": { |
| "AutoConfig": "configuration_avhubert.AVHubertConfig", |
| "AutoModel": "modeling_avhubert.AVHubertModel" |
| }, |
| "conv_bias": false, |
| "conv_dim": [ |
| 512, |
| 512, |
| 512, |
| 512, |
| 512, |
| 512, |
| 512 |
| ], |
| "conv_kernel": [ |
| 10, |
| 3, |
| 3, |
| 3, |
| 3, |
| 2, |
| 2 |
| ], |
| "conv_pos": 128, |
| "conv_pos_groups": 16, |
| "conv_stride": [ |
| 5, |
| 2, |
| 2, |
| 2, |
| 2, |
| 2, |
| 2 |
| ], |
| "ctc_loss_reduction": "mean", |
| "ctc_loss_weight": 0.3, |
| "ctc_zero_infinity": false, |
| "decoder_activation_dropout": 0.0, |
| "decoder_attention_dropout": 0.1, |
| "decoder_attention_heads": 4, |
| "decoder_dropout": 0.1, |
| "decoder_embed_dim": 768, |
| "decoder_ffn_embed_dim": 3072, |
| "decoder_layerdrop": 0.0, |
| "decoder_layers": 6, |
| "decoder_learned_pos": false, |
| "decoder_normalize_before": false, |
| "do_stable_layer_norm": true, |
| "dropout": 0.1, |
| "dropout_features": 0.1, |
| "dropout_input": 0.1, |
| "encoder_attention_heads": 12, |
| "encoder_embed_dim": 768, |
| "encoder_ffn_embed_dim": 3072, |
| "encoder_layerdrop": 0.05, |
| "encoder_layers": 12, |
| "extractor_mode": "default", |
| "feature_grad_mult": 0.1, |
| "final_dim": 256, |
| "final_dropout": 0.0, |
| "freeze_base_model": false, |
| "freeze_feature_encoder": false, |
| "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", |
| "15": "LABEL_15", |
| "16": "LABEL_16", |
| "17": "LABEL_17", |
| "18": "LABEL_18", |
| "19": "LABEL_19", |
| "20": "LABEL_20", |
| "21": "LABEL_21", |
| "22": "LABEL_22", |
| "23": "LABEL_23", |
| "24": "LABEL_24", |
| "25": "LABEL_25", |
| "26": "LABEL_26", |
| "27": "LABEL_27", |
| "28": "LABEL_28", |
| "29": "LABEL_29", |
| "30": "LABEL_30", |
| "31": "LABEL_31", |
| "32": "LABEL_32", |
| "33": "LABEL_33", |
| "34": "LABEL_34", |
| "35": "LABEL_35", |
| "36": "LABEL_36", |
| "37": "LABEL_37", |
| "38": "LABEL_38", |
| "39": "LABEL_39", |
| "40": "LABEL_40", |
| "41": "LABEL_41", |
| "42": "LABEL_42", |
| "43": "LABEL_43", |
| "44": "LABEL_44", |
| "45": "LABEL_45", |
| "46": "LABEL_46", |
| "47": "LABEL_47", |
| "48": "LABEL_48", |
| "49": "LABEL_49", |
| "50": "LABEL_50", |
| "51": "LABEL_51", |
| "52": "LABEL_52", |
| "53": "LABEL_53", |
| "54": "LABEL_54", |
| "55": "LABEL_55", |
| "56": "LABEL_56", |
| "57": "LABEL_57", |
| "58": "LABEL_58", |
| "59": "LABEL_59", |
| "60": "LABEL_60", |
| "61": "LABEL_61", |
| "62": "LABEL_62", |
| "63": "LABEL_63", |
| "64": "LABEL_64", |
| "65": "LABEL_65", |
| "66": "LABEL_66", |
| "67": "LABEL_67", |
| "68": "LABEL_68", |
| "69": "LABEL_69", |
| "70": "LABEL_70", |
| "71": "LABEL_71", |
| "72": "LABEL_72", |
| "73": "LABEL_73", |
| "74": "LABEL_74", |
| "75": "LABEL_75", |
| "76": "LABEL_76", |
| "77": "LABEL_77", |
| "78": "LABEL_78", |
| "79": "LABEL_79", |
| "80": "LABEL_80", |
| "81": "LABEL_81", |
| "82": "LABEL_82", |
| "83": "LABEL_83", |
| "84": "LABEL_84", |
| "85": "LABEL_85", |
| "86": "LABEL_86", |
| "87": "LABEL_87", |
| "88": "LABEL_88", |
| "89": "LABEL_89", |
| "90": "LABEL_90", |
| "91": "LABEL_91", |
| "92": "LABEL_92", |
| "93": "LABEL_93", |
| "94": "LABEL_94", |
| "95": "LABEL_95", |
| "96": "LABEL_96", |
| "97": "LABEL_97", |
| "98": "LABEL_98", |
| "99": "LABEL_99" |
| }, |
| "initializer_range": 0.02, |
| "input_modality": "image", |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1, |
| "LABEL_10": 10, |
| "LABEL_11": 11, |
| "LABEL_12": 12, |
| "LABEL_13": 13, |
| "LABEL_14": 14, |
| "LABEL_15": 15, |
| "LABEL_16": 16, |
| "LABEL_17": 17, |
| "LABEL_18": 18, |
| "LABEL_19": 19, |
| "LABEL_2": 2, |
| "LABEL_20": 20, |
| "LABEL_21": 21, |
| "LABEL_22": 22, |
| "LABEL_23": 23, |
| "LABEL_24": 24, |
| "LABEL_25": 25, |
| "LABEL_26": 26, |
| "LABEL_27": 27, |
| "LABEL_28": 28, |
| "LABEL_29": 29, |
| "LABEL_3": 3, |
| "LABEL_30": 30, |
| "LABEL_31": 31, |
| "LABEL_32": 32, |
| "LABEL_33": 33, |
| "LABEL_34": 34, |
| "LABEL_35": 35, |
| "LABEL_36": 36, |
| "LABEL_37": 37, |
| "LABEL_38": 38, |
| "LABEL_39": 39, |
| "LABEL_4": 4, |
| "LABEL_40": 40, |
| "LABEL_41": 41, |
| "LABEL_42": 42, |
| "LABEL_43": 43, |
| "LABEL_44": 44, |
| "LABEL_45": 45, |
| "LABEL_46": 46, |
| "LABEL_47": 47, |
| "LABEL_48": 48, |
| "LABEL_49": 49, |
| "LABEL_5": 5, |
| "LABEL_50": 50, |
| "LABEL_51": 51, |
| "LABEL_52": 52, |
| "LABEL_53": 53, |
| "LABEL_54": 54, |
| "LABEL_55": 55, |
| "LABEL_56": 56, |
| "LABEL_57": 57, |
| "LABEL_58": 58, |
| "LABEL_59": 59, |
| "LABEL_6": 6, |
| "LABEL_60": 60, |
| "LABEL_61": 61, |
| "LABEL_62": 62, |
| "LABEL_63": 63, |
| "LABEL_64": 64, |
| "LABEL_65": 65, |
| "LABEL_66": 66, |
| "LABEL_67": 67, |
| "LABEL_68": 68, |
| "LABEL_69": 69, |
| "LABEL_7": 7, |
| "LABEL_70": 70, |
| "LABEL_71": 71, |
| "LABEL_72": 72, |
| "LABEL_73": 73, |
| "LABEL_74": 74, |
| "LABEL_75": 75, |
| "LABEL_76": 76, |
| "LABEL_77": 77, |
| "LABEL_78": 78, |
| "LABEL_79": 79, |
| "LABEL_8": 8, |
| "LABEL_80": 80, |
| "LABEL_81": 81, |
| "LABEL_82": 82, |
| "LABEL_83": 83, |
| "LABEL_84": 84, |
| "LABEL_85": 85, |
| "LABEL_86": 86, |
| "LABEL_87": 87, |
| "LABEL_88": 88, |
| "LABEL_89": 89, |
| "LABEL_9": 9, |
| "LABEL_90": 90, |
| "LABEL_91": 91, |
| "LABEL_92": 92, |
| "LABEL_93": 93, |
| "LABEL_94": 94, |
| "LABEL_95": 95, |
| "LABEL_96": 96, |
| "LABEL_97": 97, |
| "LABEL_98": 98, |
| "LABEL_99": 99 |
| }, |
| "label_rate": 25, |
| "latent_temp": [ |
| 2, |
| 0.5, |
| 0.999995 |
| ], |
| "layer_norm_first": true, |
| "logit_temp": 0.1, |
| "loss_weights": [ |
| 10.0 |
| ], |
| "mask_channel_length": 10, |
| "mask_channel_min_space": 1, |
| "mask_channel_other": 0.0, |
| "mask_channel_prob": 0.0, |
| "mask_channel_selection": "static", |
| "mask_length_audio": 10, |
| "mask_length_image": 5, |
| "mask_min_space": 1, |
| "mask_other": 0.0, |
| "mask_prob_audio": 0.8, |
| "mask_prob_image": 0.3, |
| "mask_selection": "static", |
| "masking_type": "input", |
| "max_target_positions": 2048, |
| "modality_copy": 0.0, |
| "modality_dropout": 0.5, |
| "modality_fuse": "concat", |
| "modality_switch": 0.0, |
| "model_type": "avhubert", |
| "no_mask_channel_overlap": false, |
| "no_mask_overlap": false, |
| "no_scale_embedding": true, |
| "no_token_positional_embeddings": false, |
| "pred_masked_weight": 1.0, |
| "pred_nomask_weight": 0.0, |
| "resnet_relu_type": "prelu", |
| "resnet_weights": null, |
| "sample_rate": 25, |
| "selection_type": "same_seq", |
| "share_decoder_input_output_embed": false, |
| "sim_type": "cosine", |
| "skip_masked": false, |
| "skip_nomask": false, |
| "special_ids": null, |
| "sub_encoder_layers": 0, |
| "target_glu": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.53.3", |
| "untie_final_proj": true, |
| "vocab_size": null |
| } |
|
|
