JBJoyce commited on
Commit
0caacc1
1 Parent(s): 2268d50

Add model and feature extractor

Browse files
Files changed (3) hide show
  1. config.json +183 -0
  2. preprocessor_config.json +9 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "output_dir/checkpoint-450",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForSequenceClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "sum",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "id2label": {
59
+ "0": "Yes",
60
+ "1": "No",
61
+ "2": "Up",
62
+ "3": "Down",
63
+ "4": "Left",
64
+ "5": "Right",
65
+ "6": "On",
66
+ "7": "Off",
67
+ "8": "Stop",
68
+ "9": "Go",
69
+ "10": "Zero",
70
+ "11": "One",
71
+ "12": "Two",
72
+ "13": "Three",
73
+ "14": "Four",
74
+ "15": "Five",
75
+ "16": "Six",
76
+ "17": "Seven",
77
+ "18": "Eight",
78
+ "19": "Nine",
79
+ "20": "Bed",
80
+ "21": "Bird",
81
+ "22": "Cat",
82
+ "23": "Dog",
83
+ "24": "Happy",
84
+ "25": "House",
85
+ "26": "Marvin",
86
+ "27": "Sheila",
87
+ "28": "Tree",
88
+ "29": "Wow",
89
+ "30": "_Silence_"
90
+ },
91
+ "initializer_range": 0.02,
92
+ "intermediate_size": 3072,
93
+ "label2id": {
94
+ "Bed": "20",
95
+ "Bird": "21",
96
+ "Cat": "22",
97
+ "Dog": "23",
98
+ "Down": "3",
99
+ "Eight": "18",
100
+ "Five": "15",
101
+ "Four": "14",
102
+ "Go": "9",
103
+ "Happy": "24",
104
+ "House": "25",
105
+ "Left": "4",
106
+ "Marvin": "26",
107
+ "Nine": "19",
108
+ "No": "1",
109
+ "Off": "7",
110
+ "On": "6",
111
+ "One": "11",
112
+ "Right": "5",
113
+ "Seven": "17",
114
+ "Sheila": "27",
115
+ "Six": "16",
116
+ "Stop": "8",
117
+ "Three": "13",
118
+ "Tree": "28",
119
+ "Two": "12",
120
+ "Up": "2",
121
+ "Wow": "29",
122
+ "Yes": "0",
123
+ "Zero": "10",
124
+ "_Silence_": "30"
125
+ },
126
+ "layer_norm_eps": 1e-05,
127
+ "layerdrop": 0.0,
128
+ "mask_channel_length": 10,
129
+ "mask_channel_min_space": 1,
130
+ "mask_channel_other": 0.0,
131
+ "mask_channel_prob": 0.0,
132
+ "mask_channel_selection": "static",
133
+ "mask_feature_length": 10,
134
+ "mask_feature_min_masks": 0,
135
+ "mask_feature_prob": 0.0,
136
+ "mask_time_length": 10,
137
+ "mask_time_min_masks": 2,
138
+ "mask_time_min_space": 1,
139
+ "mask_time_other": 0.0,
140
+ "mask_time_prob": 0.05,
141
+ "mask_time_selection": "static",
142
+ "model_type": "wav2vec2",
143
+ "no_mask_channel_overlap": false,
144
+ "no_mask_time_overlap": false,
145
+ "num_adapter_layers": 3,
146
+ "num_attention_heads": 12,
147
+ "num_codevector_groups": 2,
148
+ "num_codevectors_per_group": 320,
149
+ "num_conv_pos_embedding_groups": 16,
150
+ "num_conv_pos_embeddings": 128,
151
+ "num_feat_extract_layers": 7,
152
+ "num_hidden_layers": 12,
153
+ "num_negatives": 100,
154
+ "output_hidden_size": 768,
155
+ "pad_token_id": 0,
156
+ "proj_codevector_dim": 256,
157
+ "tdnn_dilation": [
158
+ 1,
159
+ 2,
160
+ 3,
161
+ 1,
162
+ 1
163
+ ],
164
+ "tdnn_dim": [
165
+ 512,
166
+ 512,
167
+ 512,
168
+ 512,
169
+ 1500
170
+ ],
171
+ "tdnn_kernel": [
172
+ 5,
173
+ 3,
174
+ 3,
175
+ 1,
176
+ 1
177
+ ],
178
+ "torch_dtype": "float32",
179
+ "transformers_version": "4.26.1",
180
+ "use_weighted_layer_sum": false,
181
+ "vocab_size": 32,
182
+ "xvector_output_dim": 512
183
+ }
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": 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 sha256:0d4822b752ebfebfd1d3829477e144c35f722351b39a0762b001a8cdc41282a5
3
+ size 378377257