int0thewind commited on
Commit
d3fb1fa
1 Parent(s): 0635888

Upload 3 files

Browse files

Upload models and configurations

Files changed (3) hide show
  1. config.json +95 -0
  2. preprocessor_config.json +9 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "adapter_kernel_size": 3,
4
+ "adapter_stride": 2,
5
+ "add_adapter": false,
6
+ "architectures": [
7
+ "Data2VecAudioModel"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "bos_token_id": 1,
11
+ "classifier_proj_size": 256,
12
+ "conv_bias": false,
13
+ "conv_dim": [
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "conv_kernel": [
23
+ 10,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 2,
29
+ 2
30
+ ],
31
+ "conv_pos_kernel_size": 19,
32
+ "conv_stride": [
33
+ 5,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2
40
+ ],
41
+ "ctc_loss_reduction": "sum",
42
+ "ctc_zero_infinity": false,
43
+ "eos_token_id": 2,
44
+ "feat_extract_activation": "gelu",
45
+ "feat_proj_dropout": 0.0,
46
+ "final_dropout": 0.1,
47
+ "hidden_act": "gelu",
48
+ "hidden_dropout": 0.1,
49
+ "hidden_size": 768,
50
+ "initializer_range": 0.02,
51
+ "intermediate_size": 3072,
52
+ "layer_norm_eps": 1e-05,
53
+ "layerdrop": 0.1,
54
+ "mask_feature_length": 10,
55
+ "mask_feature_min_masks": 0,
56
+ "mask_feature_prob": 0.0,
57
+ "mask_time_length": 10,
58
+ "mask_time_min_masks": 2,
59
+ "mask_time_prob": 0.05,
60
+ "model_type": "data2vec-audio",
61
+ "num_adapter_layers": 3,
62
+ "num_attention_heads": 12,
63
+ "num_conv_pos_embedding_groups": 16,
64
+ "num_conv_pos_embeddings": 5,
65
+ "num_feat_extract_layers": 7,
66
+ "num_hidden_layers": 12,
67
+ "output_hidden_size": 768,
68
+ "pad_token_id": 0,
69
+ "tdnn_dilation": [
70
+ 1,
71
+ 2,
72
+ 3,
73
+ 1,
74
+ 1
75
+ ],
76
+ "tdnn_dim": [
77
+ 512,
78
+ 512,
79
+ 512,
80
+ 512,
81
+ 1500
82
+ ],
83
+ "tdnn_kernel": [
84
+ 5,
85
+ 3,
86
+ 3,
87
+ 1,
88
+ 1
89
+ ],
90
+ "torch_dtype": "float32",
91
+ "transformers_version": "4.21.3",
92
+ "use_weighted_layer_sum": false,
93
+ "vocab_size": 32,
94
+ "xvector_output_dim": 512
95
+ }
preprocessor_config.json ADDED
@@ -0,0 +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": true,
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:d942ad4a2db28aed92da3d664b12570a61065c9ff5bba5c21174924431939176
3
+ size 372729461