Lesson1results / config.json
hamza666's picture
Model save
cc2c4bc verified
raw
history blame contribute delete
No virus
3.7 kB
{
"_name_or_path": "facebook/wav2vec2-base",
"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": "\u062f",
"1": "\u0630",
"10": "\u0631",
"11": "\u0635",
"12": "\u0646",
"13": "\u064a",
"14": "\u0642",
"15": "\u062d",
"16": "\u0628",
"17": "\u0648",
"18": "\u0643",
"19": "\u062b",
"2": "\u0639",
"20": "\u0644",
"21": "\u0633",
"22": "\u0636",
"23": "\u0645",
"24": "\u062e",
"25": "\u062c",
"26": "\u063a",
"27": "\u0638",
"3": "\u0632",
"4": "\u0647",
"5": "\u062a",
"6": "\u0627",
"7": "\u0641",
"8": "\u0637",
"9": "\u0634"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"\u0627": "6",
"\u0628": "16",
"\u062a": "5",
"\u062b": "19",
"\u062c": "25",
"\u062d": "15",
"\u062e": "24",
"\u062f": "0",
"\u0630": "1",
"\u0631": "10",
"\u0632": "3",
"\u0633": "21",
"\u0634": "9",
"\u0635": "11",
"\u0636": "22",
"\u0637": "8",
"\u0638": "27",
"\u0639": "2",
"\u063a": "26",
"\u0641": "7",
"\u0642": "14",
"\u0643": "18",
"\u0644": "20",
"\u0645": "23",
"\u0646": "12",
"\u0647": "4",
"\u0648": "17",
"\u064a": "13"
},
"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": "4.42.3",
"use_weighted_layer_sum": false,
"vocab_size": 32,
"xvector_output_dim": 512
}