Hugging Face's logo

alirzb
/
init_Wav2Vec

PyTorch
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
alirzb commited on
Commit
8c8db15
·
verified ·
1 Parent(s): a8473d6

Training in progress, epoch 0

Browse files
Files changed (4) hide show
  1. config.json +126 -126
  2. preprocessor_config.json +9 -9
  3. pytorch_model.bin +3 -0
  4. training_args.bin +2 -2
config.json CHANGED
@@ -1,126 +1,126 @@
1
- {
2
- "_name_or_path": "facebook/wav2vec2-base",
3
- "activation_dropout": 0.0,
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
- "Wav2Vec2ForSequenceClassification"
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": false,
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": false,
49
- "eos_token_id": 2,
50
- "feat_extract_activation": "gelu",
51
- "feat_extract_norm": "group",
52
- "feat_proj_dropout": 0.1,
53
- "feat_quantizer_dropout": 0.0,
54
- "final_dropout": 0.0,
55
- "freeze_feat_extract_train": true,
56
- "hidden_act": "gelu",
57
- "hidden_dropout": 0.1,
58
- "hidden_size": 768,
59
- "id2label": {
60
- "0": "Benign",
61
- "1": "Interm"
62
- },
63
- "initializer_range": 0.02,
64
- "intermediate_size": 3072,
65
- "label2id": {
66
- "Benign": "0",
67
- "Interm": "1"
68
- },
69
- "layer_norm_eps": 1e-05,
70
- "layerdrop": 0.0,
71
- "mask_channel_length": 10,
72
- "mask_channel_min_space": 1,
73
- "mask_channel_other": 0.0,
74
- "mask_channel_prob": 0.0,
75
- "mask_channel_selection": "static",
76
- "mask_feature_length": 10,
77
- "mask_feature_min_masks": 0,
78
- "mask_feature_prob": 0.0,
79
- "mask_time_length": 10,
80
- "mask_time_min_masks": 2,
81
- "mask_time_min_space": 1,
82
- "mask_time_other": 0.0,
83
- "mask_time_prob": 0.05,
84
- "mask_time_selection": "static",
85
- "model_type": "wav2vec2",
86
- "no_mask_channel_overlap": false,
87
- "no_mask_time_overlap": false,
88
- "num_adapter_layers": 3,
89
- "num_attention_heads": 12,
90
- "num_codevector_groups": 2,
91
- "num_codevectors_per_group": 320,
92
- "num_conv_pos_embedding_groups": 16,
93
- "num_conv_pos_embeddings": 128,
94
- "num_feat_extract_layers": 7,
95
- "num_hidden_layers": 12,
96
- "num_negatives": 100,
97
- "output_hidden_size": 768,
98
- "pad_token_id": 0,
99
- "proj_codevector_dim": 256,
100
- "tdnn_dilation": [
101
- 1,
102
- 2,
103
- 3,
104
- 1,
105
- 1
106
- ],
107
- "tdnn_dim": [
108
- 512,
109
- 512,
110
- 512,
111
- 512,
112
- 1500
113
- ],
114
- "tdnn_kernel": [
115
- 5,
116
- 3,
117
- 3,
118
- 1,
119
- 1
120
- ],
121
- "torch_dtype": "float32",
122
- "transformers_version": "4.44.1",
123
- "use_weighted_layer_sum": false,
124
- "vocab_size": 32,
125
- "xvector_output_dim": 512
126
- }
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
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
+ "Wav2Vec2ForSequenceClassification"
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": false,
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": false,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "freeze_feat_extract_train": true,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 768,
59
+ "id2label": {
60
+ "0": "Benign",
61
+ "1": "Interm"
62
+ },
63
+ "initializer_range": 0.02,
64
+ "intermediate_size": 3072,
65
+ "label2id": {
66
+ "Benign": "0",
67
+ "Interm": "1"
68
+ },
69
+ "layer_norm_eps": 1e-05,
70
+ "layerdrop": 0.0,
71
+ "mask_channel_length": 10,
72
+ "mask_channel_min_space": 1,
73
+ "mask_channel_other": 0.0,
74
+ "mask_channel_prob": 0.0,
75
+ "mask_channel_selection": "static",
76
+ "mask_feature_length": 10,
77
+ "mask_feature_min_masks": 0,
78
+ "mask_feature_prob": 0.0,
79
+ "mask_time_length": 10,
80
+ "mask_time_min_masks": 2,
81
+ "mask_time_min_space": 1,
82
+ "mask_time_other": 0.0,
83
+ "mask_time_prob": 0.05,
84
+ "mask_time_selection": "static",
85
+ "model_type": "wav2vec2",
86
+ "no_mask_channel_overlap": false,
87
+ "no_mask_time_overlap": false,
88
+ "num_adapter_layers": 3,
89
+ "num_attention_heads": 12,
90
+ "num_codevector_groups": 2,
91
+ "num_codevectors_per_group": 320,
92
+ "num_conv_pos_embedding_groups": 16,
93
+ "num_conv_pos_embeddings": 128,
94
+ "num_feat_extract_layers": 7,
95
+ "num_hidden_layers": 12,
96
+ "num_negatives": 100,
97
+ "output_hidden_size": 768,
98
+ "pad_token_id": 0,
99
+ "proj_codevector_dim": 256,
100
+ "tdnn_dilation": [
101
+ 1,
102
+ 2,
103
+ 3,
104
+ 1,
105
+ 1
106
+ ],
107
+ "tdnn_dim": [
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 512,
112
+ 1500
113
+ ],
114
+ "tdnn_kernel": [
115
+ 5,
116
+ 3,
117
+ 3,
118
+ 1,
119
+ 1
120
+ ],
121
+ "torch_dtype": "float32",
122
+ "transformers_version": "4.32.1",
123
+ "use_weighted_layer_sum": false,
124
+ "vocab_size": 32,
125
+ "xvector_output_dim": 512
126
+ }
preprocessor_config.json CHANGED
@@ -1,9 +1,9 @@
1
- {
2
- "do_normalize": true,
3
- "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
- "feature_size": 1,
5
- "padding_side": "right",
6
- "padding_value": 0.0,
7
- "return_attention_mask": false,
8
- "sampling_rate": 16000
9
- }
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8fc771f397b2f6464e99744e22ae94890c9b8b6addcb40b8f2573a865269b47
3
+ size 378350950
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae96459f103e142d00ee549f101d2d105f10fdf40307f0ca6063db541cc5f8a9
3
- size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae6177f15a4d93080649083d8b7c979961ffc08dce259a67d762bc5deaf86b0
3
+ size 4472