|
{ |
|
"_name_or_path": "/home/ubuntu/24Spr_CMagee_LanguageDetection/wav2vec2_capstone", |
|
"activation_dropout": 0.0, |
|
"adapter_attn_dim": null, |
|
"adapter_kernel_size": 3, |
|
"adapter_stride": 2, |
|
"add_adapter": false, |
|
"apply_spec_augment": true, |
|
"architectures": [ |
|
"Wav2Vec2ForSequenceClassification" |
|
], |
|
"attention_dropout": 0.1, |
|
"bos_token_id": 1, |
|
"classifier_proj_size": 256, |
|
"codevector_dim": 256, |
|
"contrastive_logits_temperature": 0.1, |
|
"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, |
|
"diversity_loss_weight": 0.1, |
|
"do_stable_layer_norm": false, |
|
"eos_token_id": 2, |
|
"feat_extract_activation": "gelu", |
|
"feat_extract_norm": "group", |
|
"feat_proj_dropout": 0.1, |
|
"feat_quantizer_dropout": 0.0, |
|
"final_dropout": 0.0, |
|
"freeze_feat_extract_train": true, |
|
"hidden_act": "gelu", |
|
"hidden_dropout": 0.1, |
|
"hidden_size": 768, |
|
"id2label": { |
|
"0": "en", |
|
"1": "ca", |
|
"2": "rw", |
|
"3": "be", |
|
"4": "eo", |
|
"5": "de", |
|
"6": "fr", |
|
"7": "kab", |
|
"8": "es", |
|
"9": "lg", |
|
"10": "sw", |
|
"11": "fa", |
|
"12": "it", |
|
"13": "mhr", |
|
"14": "zh-CN", |
|
"15": "ba", |
|
"16": "ta", |
|
"17": "ru", |
|
"18": "eu", |
|
"19": "th", |
|
"20": "pt", |
|
"21": "pl", |
|
"22": "ja" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"label2id": { |
|
"ba": "15", |
|
"be": "3", |
|
"ca": "1", |
|
"de": "5", |
|
"en": "0", |
|
"eo": "4", |
|
"es": "8", |
|
"eu": "18", |
|
"fa": "11", |
|
"fr": "6", |
|
"it": "12", |
|
"ja": "22", |
|
"kab": "7", |
|
"lg": "9", |
|
"mhr": "13", |
|
"pl": "21", |
|
"pt": "20", |
|
"ru": "17", |
|
"rw": "2", |
|
"sw": "10", |
|
"ta": "16", |
|
"th": "19", |
|
"zh-CN": "14" |
|
}, |
|
"layer_norm_eps": 1e-05, |
|
"layerdrop": 0.0, |
|
"mask_channel_length": 10, |
|
"mask_channel_min_space": 1, |
|
"mask_channel_other": 0.0, |
|
"mask_channel_prob": 0.0, |
|
"mask_channel_selection": "static", |
|
"mask_feature_length": 10, |
|
"mask_feature_min_masks": 0, |
|
"mask_feature_prob": 0.0, |
|
"mask_time_length": 10, |
|
"mask_time_min_masks": 2, |
|
"mask_time_min_space": 1, |
|
"mask_time_other": 0.0, |
|
"mask_time_prob": 0.05, |
|
"mask_time_selection": "static", |
|
"model_type": "wav2vec2", |
|
"no_mask_channel_overlap": false, |
|
"no_mask_time_overlap": false, |
|
"num_adapter_layers": 3, |
|
"num_attention_heads": 12, |
|
"num_codevector_groups": 2, |
|
"num_codevectors_per_group": 320, |
|
"num_conv_pos_embedding_groups": 16, |
|
"num_conv_pos_embeddings": 128, |
|
"num_feat_extract_layers": 7, |
|
"num_hidden_layers": 12, |
|
"num_negatives": 100, |
|
"output_hidden_size": 768, |
|
"pad_token_id": 0, |
|
"proj_codevector_dim": 256, |
|
"tdnn_dilation": [ |
|
1, |
|
2, |
|
3, |
|
1, |
|
1 |
|
], |
|
"tdnn_dim": [ |
|
512, |
|
512, |
|
512, |
|
512, |
|
1500 |
|
], |
|
"tdnn_kernel": [ |
|
5, |
|
3, |
|
3, |
|
1, |
|
1 |
|
], |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.36.2", |
|
"use_weighted_layer_sum": false, |
|
"vocab_size": 32, |
|
"xvector_output_dim": 512 |
|
} |
|
|