Utsaha commited on
Commit
aebcba8
1 Parent(s): bbbd935

Upload 7 files

Browse files
fine_tuned_model/config.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
93
+ "initializer_range": 0.02,
94
+ "intermediate_size": 3072,
95
+ "label2id": {
96
+ "LABEL_0": 0,
97
+ "LABEL_1": 1,
98
+ "LABEL_10": 10,
99
+ "LABEL_11": 11,
100
+ "LABEL_12": 12,
101
+ "LABEL_13": 13,
102
+ "LABEL_14": 14,
103
+ "LABEL_15": 15,
104
+ "LABEL_16": 16,
105
+ "LABEL_17": 17,
106
+ "LABEL_18": 18,
107
+ "LABEL_19": 19,
108
+ "LABEL_2": 2,
109
+ "LABEL_20": 20,
110
+ "LABEL_21": 21,
111
+ "LABEL_22": 22,
112
+ "LABEL_23": 23,
113
+ "LABEL_24": 24,
114
+ "LABEL_25": 25,
115
+ "LABEL_26": 26,
116
+ "LABEL_27": 27,
117
+ "LABEL_28": 28,
118
+ "LABEL_29": 29,
119
+ "LABEL_3": 3,
120
+ "LABEL_4": 4,
121
+ "LABEL_5": 5,
122
+ "LABEL_6": 6,
123
+ "LABEL_7": 7,
124
+ "LABEL_8": 8,
125
+ "LABEL_9": 9
126
+ },
127
+ "layer_norm_eps": 1e-05,
128
+ "layerdrop": 0.1,
129
+ "mask_feature_length": 10,
130
+ "mask_feature_min_masks": 0,
131
+ "mask_feature_prob": 0.0,
132
+ "mask_time_length": 10,
133
+ "mask_time_min_masks": 2,
134
+ "mask_time_prob": 0.05,
135
+ "model_type": "wav2vec2",
136
+ "num_adapter_layers": 3,
137
+ "num_attention_heads": 12,
138
+ "num_codevector_groups": 2,
139
+ "num_codevectors_per_group": 320,
140
+ "num_conv_pos_embedding_groups": 16,
141
+ "num_conv_pos_embeddings": 128,
142
+ "num_feat_extract_layers": 7,
143
+ "num_hidden_layers": 12,
144
+ "num_negatives": 100,
145
+ "output_hidden_size": 768,
146
+ "pad_token_id": 0,
147
+ "proj_codevector_dim": 256,
148
+ "tdnn_dilation": [
149
+ 1,
150
+ 2,
151
+ 3,
152
+ 1,
153
+ 1
154
+ ],
155
+ "tdnn_dim": [
156
+ 512,
157
+ 512,
158
+ 512,
159
+ 512,
160
+ 1500
161
+ ],
162
+ "tdnn_kernel": [
163
+ 5,
164
+ 3,
165
+ 3,
166
+ 1,
167
+ 1
168
+ ],
169
+ "torch_dtype": "float32",
170
+ "transformers_version": "4.42.0.dev0",
171
+ "use_weighted_layer_sum": false,
172
+ "vocab_size": 32,
173
+ "xvector_output_dim": 512
174
+ }
fine_tuned_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edf894eb141ac92448888c0960fda1a0d51ccf61d035d54fb465b8513c022c21
3
+ size 378331160
fine_tuned_model/preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": false,
9
+ "sampling_rate": 16000
10
+ }
fine_tuned_model/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
fine_tuned_model/tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "do_normalize": true,
40
+ "eos_token": "</s>",
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<pad>",
43
+ "processor_class": "Wav2Vec2Processor",
44
+ "replace_word_delimiter_char": " ",
45
+ "return_attention_mask": false,
46
+ "target_lang": null,
47
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
48
+ "unk_token": "<unk>",
49
+ "word_delimiter_token": "|"
50
+ }
fine_tuned_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29c62f5aad4f4e0e8cc4e3195a73c32e556e3416a685b64f45e219567e49731c
3
+ size 5112
fine_tuned_model/vocab.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 27,
3
+ "</s>": 2,
4
+ "<pad>": 0,
5
+ "<s>": 1,
6
+ "<unk>": 3,
7
+ "A": 7,
8
+ "B": 24,
9
+ "C": 19,
10
+ "D": 14,
11
+ "E": 5,
12
+ "F": 20,
13
+ "G": 21,
14
+ "H": 11,
15
+ "I": 10,
16
+ "J": 29,
17
+ "K": 26,
18
+ "L": 15,
19
+ "M": 17,
20
+ "N": 9,
21
+ "O": 8,
22
+ "P": 23,
23
+ "Q": 30,
24
+ "R": 13,
25
+ "S": 12,
26
+ "T": 6,
27
+ "U": 16,
28
+ "V": 25,
29
+ "W": 18,
30
+ "X": 28,
31
+ "Y": 22,
32
+ "Z": 31,
33
+ "|": 4
34
+ }