Hugging Face's logo

aryamtos
/
wav2vec2-large-xlsr-bp-finetuning-model

Transformers
PyTorch
TensorBoard
wav2vec2
Inference Endpoints
Model card Files Metrics Community
aryamtos commited on
Commit
22fad07
·
1 Parent(s): 38bc84f

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +121 -0
config.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lgris/wav2vec2-large-xlsr-open-brazilian-portuguese",
3
+ "activation_dropout": 0.1,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForSpeechClassification"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "sum",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.1,
56
+ "finetuning_task": "wav2vec2_clf",
57
+ "gradient_checkpointing": false,
58
+ "hidden_act": "gelu",
59
+ "hidden_dropout": 0.1,
60
+ "hidden_dropout_prob": 0.1,
61
+ "hidden_size": 1024,
62
+ "id2label": {
63
+ "0": "re",
64
+ "1": "sp"
65
+ },
66
+ "initializer_range": 0.02,
67
+ "intermediate_size": 4096,
68
+ "label2id": {
69
+ "re": 0,
70
+ "sp": 1
71
+ },
72
+ "layer_norm_eps": 1e-05,
73
+ "layerdrop": 0.1,
74
+ "mask_feature_length": 10,
75
+ "mask_feature_min_masks": 0,
76
+ "mask_feature_prob": 0.0,
77
+ "mask_time_length": 10,
78
+ "mask_time_min_masks": 2,
79
+ "mask_time_prob": 0.05,
80
+ "model_type": "wav2vec2",
81
+ "num_adapter_layers": 3,
82
+ "num_attention_heads": 16,
83
+ "num_codevector_groups": 2,
84
+ "num_codevectors_per_group": 320,
85
+ "num_conv_pos_embedding_groups": 16,
86
+ "num_conv_pos_embeddings": 128,
87
+ "num_feat_extract_layers": 7,
88
+ "num_hidden_layers": 24,
89
+ "num_negatives": 100,
90
+ "output_hidden_size": 1024,
91
+ "pad_token_id": 0,
92
+ "pooling_mode": "mean",
93
+ "problem_type": "single_label_classification",
94
+ "proj_codevector_dim": 256,
95
+ "tdnn_dilation": [
96
+ 1,
97
+ 2,
98
+ 3,
99
+ 1,
100
+ 1
101
+ ],
102
+ "tdnn_dim": [
103
+ 512,
104
+ 512,
105
+ 512,
106
+ 512,
107
+ 1500
108
+ ],
109
+ "tdnn_kernel": [
110
+ 5,
111
+ 3,
112
+ 3,
113
+ 1,
114
+ 1
115
+ ],
116
+ "torch_dtype": "float32",
117
+ "transformers_version": "4.34.0",
118
+ "use_weighted_layer_sum": false,
119
+ "vocab_size": 44,
120
+ "xvector_output_dim": 512
121
+ }