Hugging Face's logo

gelbanna
/
test

Transformers
PyTorch
wav2vec2_base
pretraining
Inference Endpoints
Model card Files Community
gelbanna commited on
Commit
54eefc9
•
1 Parent(s): 958628c

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +75 -109
config.json CHANGED
@@ -1,111 +1,77 @@
1
  {
2
- "_name_or_path": "facebook/wav2vec2-base-960h",
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
- "Wav2Vec2ForPreTraining"
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_dropout": 0.05,
52
- "feat_extract_norm": "group",
53
- "feat_proj_dropout": 0.0,
54
- "feat_quantizer_dropout": 0.0,
55
- "feature_grad_mult": 0.1,
56
- "final_dropout": 0.1,
57
- "gradient_checkpointing": false,
58
- "hidden_act": "gelu",
59
- "hidden_dropout": 0.1,
60
- "hidden_dropout_prob": 0.1,
61
- "hidden_size": 768,
62
- "initializer_range": 0.02,
63
- "input_form": "waveform",
64
- "intermediate_size": 3072,
65
- "layer_norm_eps": 1e-05,
66
- "layerdrop": 0.1,
67
- "mask_feature_length": 10,
68
- "mask_feature_min_masks": 0,
69
- "mask_feature_prob": 0.0,
70
- "mask_time_length": 10,
71
- "mask_time_min_masks": 2,
72
- "mask_time_prob": 0.65,
73
- "model_type": "wav2vec2",
74
- "num_adapter_layers": 3,
75
- "num_attention_heads": 12,
76
- "num_codevector_groups": 2,
77
- "num_codevectors_per_group": 320,
78
- "num_conv_pos_embedding_groups": 16,
79
- "num_conv_pos_embeddings": 128,
80
- "num_feat_extract_layers": 7,
81
- "num_hidden_layers": 12,
82
- "num_negatives": 100,
83
- "output_hidden_size": 768,
84
- "pad_token_id": 0,
85
- "proj_codevector_dim": 256,
86
- "tdnn_dilation": [
87
- 1,
88
- 2,
89
- 3,
90
- 1,
91
- 1
92
- ],
93
- "tdnn_dim": [
94
- 512,
95
- 512,
96
- 512,
97
- 512,
98
- 1500
99
- ],
100
- "tdnn_kernel": [
101
- 5,
102
- 3,
103
- 3,
104
- 1,
105
- 1
106
- ],
107
- "transformers_version": "4.33.2",
108
- "use_weighted_layer_sum": false,
109
- "vocab_size": 32,
110
- "xvector_output_dim": 512
111
  }
 
 
1
  {
2
+ "input_form": "waveform",
3
+ "_name_or_path": "facebook/wav2vec2-base-960h",
4
+ "activation_dropout": 0.1,
5
+ "apply_spec_augment": true,
6
+ "architectures": [
7
+ "Wav2Vec2ForPreTraining"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "bos_token_id": 1,
11
+ "codevector_dim": 256,
12
+ "contrastive_logits_temperature": 0.1,
13
+ "conv_bias": false,
14
+ "conv_dim": [
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512
22
+ ],
23
+ "conv_kernel": [
24
+ 10,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 3,
29
+ 2,
30
+ 2
31
+ ],
32
+ "conv_stride": [
33
+ 5,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2
40
+ ],
41
+ "diversity_loss_weight": 0.1,
42
+ "do_stable_layer_norm": false,
43
+ "eos_token_id": 2,
44
+ "feat_extract_activation": "gelu",
45
+ "feat_extract_dropout": 0.05,
46
+ "feat_extract_norm": "group",
47
+ "feat_proj_dropout": 0.0,
48
+ "feature_grad_mult": 0.1,
49
+ "feat_quantizer_dropout": 0.0,
50
+ "final_dropout": 0.1,
51
+ "gradient_checkpointing": false,
52
+ "hidden_act": "gelu",
53
+ "hidden_dropout": 0.1,
54
+ "hidden_dropout_prob": 0.1,
55
+ "hidden_size": 768,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 3072,
58
+ "layer_norm_eps": 1e-05,
59
+ "layerdrop": 0.1,
60
+ "mask_feature_length": 10,
61
+ "mask_feature_prob": 0.0,
62
+ "mask_time_length": 10,
63
+ "mask_time_prob": 0.65,
64
+ "model_type": "wav2vec2_base",
65
+ "num_attention_heads": 12,
66
+ "num_codevector_groups": 2,
67
+ "num_codevectors_per_group": 320,
68
+ "num_conv_pos_embedding_groups": 16,
69
+ "num_conv_pos_embeddings": 128,
70
+ "num_feat_extract_layers": 7,
71
+ "num_hidden_layers": 12,
72
+ "num_negatives": 100,
73
+ "pad_token_id": 0,
74
+ "proj_codevector_dim": 256,
75
+ "transformers_version": "4.12.0.dev0"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
+