speech-test commited on
Commit
ed88876
1 Parent(s): 18658be

Upload model

Browse files

Files changed (3) hide show
  1. config.json +94 -0
  2. preprocessor_config.json +9 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "SEWDModel"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 1,
9
+ "conv_bias": false,
10
+ "conv_dim": [
11
+ 64,
12
+ 128,
13
+ 128,
14
+ 128,
15
+ 128,
16
+ 256,
17
+ 256,
18
+ 256,
19
+ 256,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512
24
+ ],
25
+ "conv_kernel": [
26
+ 10,
27
+ 3,
28
+ 1,
29
+ 3,
30
+ 1,
31
+ 3,
32
+ 1,
33
+ 3,
34
+ 1,
35
+ 2,
36
+ 1,
37
+ 2,
38
+ 1
39
+ ],
40
+ "conv_stride": [
41
+ 5,
42
+ 2,
43
+ 1,
44
+ 2,
45
+ 1,
46
+ 2,
47
+ 1,
48
+ 2,
49
+ 1,
50
+ 2,
51
+ 1,
52
+ 2,
53
+ 1
54
+ ],
55
+ "ctc_loss_reduction": "sum",
56
+ "ctc_zero_infinity": false,
57
+ "eos_token_id": 2,
58
+ "feat_extract_activation": "gelu",
59
+ "feat_extract_norm": "group",
60
+ "feat_proj_dropout": 0.1,
61
+ "final_dropout": 0.0,
62
+ "hidden_act": "gelu",
63
+ "hidden_dropout": 0.1,
64
+ "hidden_size": 384,
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 1536,
67
+ "layer_norm_eps": 1e-05,
68
+ "layerdrop": 0.05,
69
+ "mask_feature_length": 10,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_prob": 0.65,
73
+ "max_position_embeddings": 512,
74
+ "model_type": "sew-d",
75
+ "norm_rel_ebd": "layer_norm",
76
+ "num_attention_heads": 6,
77
+ "num_conv_pos_embedding_groups": 16,
78
+ "num_conv_pos_embeddings": 31,
79
+ "num_feat_extract_layers": 13,
80
+ "num_hidden_layers": 12,
81
+ "pad_token_id": 0,
82
+ "pos_att_type": [
83
+ "p2c",
84
+ "c2p"
85
+ ],
86
+ "position_biased_input": false,
87
+ "position_buckets": 256,
88
+ "relative_attention": true,
89
+ "share_att_key": true,
90
+ "squeeze_factor": 2,
91
+ "torch_dtype": "float32",
92
+ "transformers_version": "4.12.0.dev0",
93
+ "vocab_size": 32
94
+ }
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,
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 sha256:2b70465278ef7f6c9d62d1e4b34b64edb47678a65776deb5a7db2537b7e505ee
3
+ size 96547593