Hugging Face's logo

moonseok
/
wav2vec_final_output

Audio Classification
Transformers
PyTorch
TensorBoard
Safetensors
audio-spectrogram-transformer
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
moonseok commited on
Commit
d2f7afe
•
1 Parent(s): c6dec7c

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. config.json +194 -0
  2. preprocessor_config.json +9 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
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
+ "Wav2Vec2ForSequenceClassification"
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_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "freeze_feat_extract_train": true,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 768,
59
+ "id2label": {
60
+ "0": 0,
61
+ "1": 1,
62
+ "10": 10,
63
+ "11": 11,
64
+ "12": 12,
65
+ "13": 13,
66
+ "14": 14,
67
+ "15": 15,
68
+ "16": 16,
69
+ "17": 17,
70
+ "18": 18,
71
+ "19": 19,
72
+ "2": 2,
73
+ "20": 20,
74
+ "21": 21,
75
+ "22": 22,
76
+ "23": 23,
77
+ "24": 24,
78
+ "25": 25,
79
+ "26": 26,
80
+ "27": 27,
81
+ "28": 28,
82
+ "29": 29,
83
+ "3": 3,
84
+ "30": 30,
85
+ "31": 31,
86
+ "32": 32,
87
+ "33": 33,
88
+ "34": 34,
89
+ "35": 35,
90
+ "4": 4,
91
+ "5": 5,
92
+ "6": 6,
93
+ "7": 7,
94
+ "8": 8,
95
+ "9": 9
96
+ },
97
+ "initializer_range": 0.02,
98
+ "intermediate_size": 3072,
99
+ "label2id": {
100
+ "0": "0",
101
+ "1": "1",
102
+ "2": "2",
103
+ "3": "3",
104
+ "4": "4",
105
+ "5": "5",
106
+ "6": "6",
107
+ "7": "7",
108
+ "8": "8",
109
+ "9": "9",
110
+ "10": "10",
111
+ "11": "11",
112
+ "12": "12",
113
+ "13": "13",
114
+ "14": "14",
115
+ "15": "15",
116
+ "16": "16",
117
+ "17": "17",
118
+ "18": "18",
119
+ "19": "19",
120
+ "20": "20",
121
+ "21": "21",
122
+ "22": "22",
123
+ "23": "23",
124
+ "24": "24",
125
+ "25": "25",
126
+ "26": "26",
127
+ "27": "27",
128
+ "28": "28",
129
+ "29": "29",
130
+ "30": "30",
131
+ "31": "31",
132
+ "32": "32",
133
+ "33": "33",
134
+ "34": "34",
135
+ "35": "35"
136
+ },
137
+ "layer_norm_eps": 1e-05,
138
+ "layerdrop": 0.0,
139
+ "mask_channel_length": 10,
140
+ "mask_channel_min_space": 1,
141
+ "mask_channel_other": 0.0,
142
+ "mask_channel_prob": 0.0,
143
+ "mask_channel_selection": "static",
144
+ "mask_feature_length": 10,
145
+ "mask_feature_min_masks": 0,
146
+ "mask_feature_prob": 0.0,
147
+ "mask_time_length": 10,
148
+ "mask_time_min_masks": 2,
149
+ "mask_time_min_space": 1,
150
+ "mask_time_other": 0.0,
151
+ "mask_time_prob": 0.05,
152
+ "mask_time_selection": "static",
153
+ "model_type": "wav2vec2",
154
+ "no_mask_channel_overlap": false,
155
+ "no_mask_time_overlap": false,
156
+ "num_adapter_layers": 3,
157
+ "num_attention_heads": 12,
158
+ "num_codevector_groups": 2,
159
+ "num_codevectors_per_group": 320,
160
+ "num_conv_pos_embedding_groups": 16,
161
+ "num_conv_pos_embeddings": 128,
162
+ "num_feat_extract_layers": 7,
163
+ "num_hidden_layers": 12,
164
+ "num_negatives": 100,
165
+ "output_hidden_size": 768,
166
+ "pad_token_id": 0,
167
+ "proj_codevector_dim": 256,
168
+ "tdnn_dilation": [
169
+ 1,
170
+ 2,
171
+ 3,
172
+ 1,
173
+ 1
174
+ ],
175
+ "tdnn_dim": [
176
+ 512,
177
+ 512,
178
+ 512,
179
+ 512,
180
+ 1500
181
+ ],
182
+ "tdnn_kernel": [
183
+ 5,
184
+ 3,
185
+ 3,
186
+ 1,
187
+ 1
188
+ ],
189
+ "torch_dtype": "float32",
190
+ "transformers_version": "4.34.1",
191
+ "use_weighted_layer_sum": false,
192
+ "vocab_size": 32,
193
+ "xvector_output_dim": 512
194
+ }
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 sha256:060922d641ae6ed42006829fd51a761471e0a9410b113de1aca268a7f30a24bf
3
+ size 378385894
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b127206d10b39a4a825e242407ff6e401bd3a2c070bf7925f9d004a49268969
3
+ size 4536