Hugging Face's logo

circulus
/
kowav2vec2-conformer-adult-v1

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2-conformer
Inference Endpoints
Model card Files Community
rippertnt commited on
Commit
3cb3c78
•
1 Parent(s): 1db9d99

add model

Browse files
Files changed (2) hide show
  1. config.json +113 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./kowav2vec2-conformer-adult-v1/checkpoint-1010000",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ConformerForCTC"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "conformer_conv_dropout": 0.1,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
18
+ "conv_depthwise_kernel_size": 31,
19
+ "conv_dim": [
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512,
26
+ 512
27
+ ],
28
+ "conv_kernel": [
29
+ 10,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 3,
34
+ 2,
35
+ 2
36
+ ],
37
+ "conv_stride": [
38
+ 5,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2,
44
+ 2
45
+ ],
46
+ "ctc_loss_reduction": "mean",
47
+ "ctc_zero_infinity": false,
48
+ "diversity_loss_weight": 0.1,
49
+ "do_stable_layer_norm": true,
50
+ "eos_token_id": 2,
51
+ "feat_extract_activation": "gelu",
52
+ "feat_extract_dropout": 0.0,
53
+ "feat_extract_norm": "layer",
54
+ "feat_proj_dropout": 0.0,
55
+ "feat_quantizer_dropout": 0.0,
56
+ "final_dropout": 0.1,
57
+ "hidden_act": "swish",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_dropout_prob": 0.1,
60
+ "hidden_size": 1024,
61
+ "initializer_range": 0.02,
62
+ "intermediate_size": 4096,
63
+ "layer_norm_eps": 1e-05,
64
+ "layerdrop": 0.1,
65
+ "mask_feature_length": 10,
66
+ "mask_feature_min_masks": 0,
67
+ "mask_feature_prob": 0.0,
68
+ "mask_time_length": 10,
69
+ "mask_time_min_masks": 2,
70
+ "mask_time_prob": 0,
71
+ "max_source_positions": 5000,
72
+ "model_type": "wav2vec2-conformer",
73
+ "num_adapter_layers": 3,
74
+ "num_attention_heads": 16,
75
+ "num_codevector_groups": 2,
76
+ "num_codevectors_per_group": 320,
77
+ "num_conv_pos_embedding_groups": 16,
78
+ "num_conv_pos_embeddings": 128,
79
+ "num_feat_extract_layers": 7,
80
+ "num_hidden_layers": 24,
81
+ "num_negatives": 100,
82
+ "output_hidden_size": 1024,
83
+ "pad_token_id": 78,
84
+ "position_embeddings_type": "relative",
85
+ "proj_codevector_dim": 768,
86
+ "rotary_embedding_base": 10000,
87
+ "tdnn_dilation": [
88
+ 1,
89
+ 2,
90
+ 3,
91
+ 1,
92
+ 1
93
+ ],
94
+ "tdnn_dim": [
95
+ 512,
96
+ 512,
97
+ 512,
98
+ 512,
99
+ 1500
100
+ ],
101
+ "tdnn_kernel": [
102
+ 5,
103
+ 3,
104
+ 3,
105
+ 1,
106
+ 1
107
+ ],
108
+ "torch_dtype": "float32",
109
+ "transformers_version": "4.21.2",
110
+ "use_weighted_layer_sum": false,
111
+ "vocab_size": 79,
112
+ "xvector_output_dim": 512
113
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d9f7a3b7264da0f27b25b593d57576482e7bb0b9b8c44a59ba85dc0511068bd
3
+ size 2475066371