SaiPatil commited on
Commit
86d1d5e
1 Parent(s): 10f9592

Upload TFWav2Vec2ForSequenceClassification

Browse files
Files changed (3) hide show
  1. README.md +49 -0
  2. config.json +183 -0
  3. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-base-960h
4
+ tags:
5
+ - generated_from_keras_callback
6
+ model-index:
7
+ - name: wav2vec
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
12
+ probably proofread and complete it, then remove this comment. -->
13
+
14
+ # wav2vec
15
+
16
+ This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - optimizer: None
38
+ - training_precision: float32
39
+
40
+ ### Training results
41
+
42
+
43
+
44
+ ### Framework versions
45
+
46
+ - Transformers 4.42.0.dev0
47
+ - TensorFlow 2.15.0
48
+ - Datasets 2.20.0
49
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
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_dropout": 0.0,
52
+ "feat_extract_norm": "group",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.1,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_dropout_prob": 0.1,
60
+ "hidden_size": 768,
61
+ "id2label": {
62
+ "0": "LABEL_0",
63
+ "1": "LABEL_1",
64
+ "2": "LABEL_2",
65
+ "3": "LABEL_3",
66
+ "4": "LABEL_4",
67
+ "5": "LABEL_5",
68
+ "6": "LABEL_6",
69
+ "7": "LABEL_7",
70
+ "8": "LABEL_8",
71
+ "9": "LABEL_9",
72
+ "10": "LABEL_10",
73
+ "11": "LABEL_11",
74
+ "12": "LABEL_12",
75
+ "13": "LABEL_13",
76
+ "14": "LABEL_14",
77
+ "15": "LABEL_15",
78
+ "16": "LABEL_16",
79
+ "17": "LABEL_17",
80
+ "18": "LABEL_18",
81
+ "19": "LABEL_19",
82
+ "20": "LABEL_20",
83
+ "21": "LABEL_21",
84
+ "22": "LABEL_22",
85
+ "23": "LABEL_23",
86
+ "24": "LABEL_24",
87
+ "25": "LABEL_25",
88
+ "26": "LABEL_26",
89
+ "27": "LABEL_27",
90
+ "28": "LABEL_28",
91
+ "29": "LABEL_29",
92
+ "30": "LABEL_30",
93
+ "31": "LABEL_31",
94
+ "32": "LABEL_32",
95
+ "33": "LABEL_33",
96
+ "34": "LABEL_34"
97
+ },
98
+ "initializer_range": 0.02,
99
+ "intermediate_size": 3072,
100
+ "label2id": {
101
+ "LABEL_0": 0,
102
+ "LABEL_1": 1,
103
+ "LABEL_10": 10,
104
+ "LABEL_11": 11,
105
+ "LABEL_12": 12,
106
+ "LABEL_13": 13,
107
+ "LABEL_14": 14,
108
+ "LABEL_15": 15,
109
+ "LABEL_16": 16,
110
+ "LABEL_17": 17,
111
+ "LABEL_18": 18,
112
+ "LABEL_19": 19,
113
+ "LABEL_2": 2,
114
+ "LABEL_20": 20,
115
+ "LABEL_21": 21,
116
+ "LABEL_22": 22,
117
+ "LABEL_23": 23,
118
+ "LABEL_24": 24,
119
+ "LABEL_25": 25,
120
+ "LABEL_26": 26,
121
+ "LABEL_27": 27,
122
+ "LABEL_28": 28,
123
+ "LABEL_29": 29,
124
+ "LABEL_3": 3,
125
+ "LABEL_30": 30,
126
+ "LABEL_31": 31,
127
+ "LABEL_32": 32,
128
+ "LABEL_33": 33,
129
+ "LABEL_34": 34,
130
+ "LABEL_4": 4,
131
+ "LABEL_5": 5,
132
+ "LABEL_6": 6,
133
+ "LABEL_7": 7,
134
+ "LABEL_8": 8,
135
+ "LABEL_9": 9
136
+ },
137
+ "layer_norm_eps": 1e-05,
138
+ "layerdrop": 0.1,
139
+ "mask_feature_length": 10,
140
+ "mask_feature_min_masks": 0,
141
+ "mask_feature_prob": 0.0,
142
+ "mask_time_length": 10,
143
+ "mask_time_min_masks": 2,
144
+ "mask_time_prob": 0.05,
145
+ "model_type": "wav2vec2",
146
+ "num_adapter_layers": 3,
147
+ "num_attention_heads": 12,
148
+ "num_codevector_groups": 2,
149
+ "num_codevectors_per_group": 320,
150
+ "num_conv_pos_embedding_groups": 16,
151
+ "num_conv_pos_embeddings": 128,
152
+ "num_feat_extract_layers": 7,
153
+ "num_hidden_layers": 12,
154
+ "num_negatives": 100,
155
+ "output_hidden_size": 768,
156
+ "pad_token_id": 0,
157
+ "proj_codevector_dim": 256,
158
+ "tdnn_dilation": [
159
+ 1,
160
+ 2,
161
+ 3,
162
+ 1,
163
+ 1
164
+ ],
165
+ "tdnn_dim": [
166
+ 512,
167
+ 512,
168
+ 512,
169
+ 512,
170
+ 1500
171
+ ],
172
+ "tdnn_kernel": [
173
+ 5,
174
+ 3,
175
+ 3,
176
+ 1,
177
+ 1
178
+ ],
179
+ "transformers_version": "4.42.0.dev0",
180
+ "use_weighted_layer_sum": false,
181
+ "vocab_size": 32,
182
+ "xvector_output_dim": 512
183
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b20ee141c2b9f87b0e9fbdcc8ab11be411b7f534e69df2c2abfa716d8cc9fe0
3
+ size 378584432