Hugging Face's logo

hts98
/
wav2vec2-ver1.8

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Model card Files
xet
Metrics Community
1
hts98 commited on
Commit
5a373bf
·
1 Parent(s): 0a00a45

Training in progress, epoch 1

Browse files
Files changed (10) hide show
  1. .gitignore +1 -0
  2. added_tokens.json +4 -0
  3. config.json +109 -0
  4. preprocessor_config.json +10 -0
  5. pytorch_model.bin +3 -0
  6. runs/Jun24_16-08-10_39a9a43c2076/events.out.tfevents.1687623549.39a9a43c2076.21544.0 +3 -0
  7. special_tokens_map.json +162 -0
  8. tokenizer_config.json +15 -0
  9. training_args.bin +3 -0
  10. vocab.json +98 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 97,
3
+ "<s>": 96
4
+ }
config.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nguyenvulebinh/wav2vec2-base-vi",
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
+ "Wav2Vec2ForCTC"
11
+ ],
12
+ "attention_dropout": 0.0,
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": "mean",
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": 0.0,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.0,
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 768,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 3072,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.0,
64
+ "mask_feature_length": 10,
65
+ "mask_feature_min_masks": 0,
66
+ "mask_feature_prob": 0.0,
67
+ "mask_time_length": 10,
68
+ "mask_time_min_masks": 2,
69
+ "mask_time_prob": 0.05,
70
+ "model_type": "wav2vec2",
71
+ "num_adapter_layers": 3,
72
+ "num_attention_heads": 12,
73
+ "num_codevector_groups": 2,
74
+ "num_codevectors_per_group": 320,
75
+ "num_conv_pos_embedding_groups": 16,
76
+ "num_conv_pos_embeddings": 128,
77
+ "num_feat_extract_layers": 7,
78
+ "num_hidden_layers": 12,
79
+ "num_negatives": 100,
80
+ "output_hidden_size": 768,
81
+ "pad_token_id": 95,
82
+ "proj_codevector_dim": 256,
83
+ "tdnn_dilation": [
84
+ 1,
85
+ 2,
86
+ 3,
87
+ 1,
88
+ 1
89
+ ],
90
+ "tdnn_dim": [
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 1500
96
+ ],
97
+ "tdnn_kernel": [
98
+ 5,
99
+ 3,
100
+ 3,
101
+ 1,
102
+ 1
103
+ ],
104
+ "torch_dtype": "float32",
105
+ "transformers_version": "4.31.0.dev0",
106
+ "use_weighted_layer_sum": false,
107
+ "vocab_size": 98,
108
+ "xvector_output_dim": 512
109
+ }
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9ccc7cbd9471077e6c2c29929b0357c324115f6e5f273641c214d20baf7b7a4
3
+ size 377861793
runs/Jun24_16-08-10_39a9a43c2076/events.out.tfevents.1687623549.39a9a43c2076.21544.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f1fe4cd2b669bf718f910aa7ccc20b23db640aa08bcba2c3f9d7b6ebd2dc6da
3
+ size 5841
special_tokens_map.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<s>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<s>",
33
+ "lstrip": false,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "</s>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<s>",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "</s>",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<s>",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "</s>",
68
+ "lstrip": false,
69
+ "normalized": true,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<s>",
75
+ "lstrip": false,
76
+ "normalized": true,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "</s>",
82
+ "lstrip": false,
83
+ "normalized": true,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<s>",
89
+ "lstrip": false,
90
+ "normalized": true,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "</s>",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "<s>",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "</s>",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "<s>",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "</s>",
124
+ "lstrip": false,
125
+ "normalized": true,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "<s>",
131
+ "lstrip": false,
132
+ "normalized": true,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "</s>",
138
+ "lstrip": false,
139
+ "normalized": true,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "<s>",
145
+ "lstrip": false,
146
+ "normalized": true,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "</s>",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ }
157
+ ],
158
+ "bos_token": "<s>",
159
+ "eos_token": "</s>",
160
+ "pad_token": "<pad>",
161
+ "unk_token": "<unk>"
162
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "processor_class": "Wav2Vec2Processor",
9
+ "replace_word_delimiter_char": " ",
10
+ "target_lang": null,
11
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
12
+ "tokenizer_file": null,
13
+ "unk_token": "<unk>",
14
+ "word_delimiter_token": "|"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a2ca18b6d5eec1a11affc4a09a515adead98c178c6c87c152b891896ad4dd58
3
+ size 3963
vocab.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<pad>": 95,
3
+ "<unk>": 94,
4
+ "a": 1,
5
+ "b": 2,
6
+ "c": 3,
7
+ "d": 4,
8
+ "e": 5,
9
+ "f": 6,
10
+ "g": 7,
11
+ "h": 8,
12
+ "i": 9,
13
+ "j": 10,
14
+ "k": 11,
15
+ "l": 12,
16
+ "m": 13,
17
+ "n": 14,
18
+ "o": 15,
19
+ "p": 16,
20
+ "q": 17,
21
+ "r": 18,
22
+ "s": 19,
23
+ "t": 20,
24
+ "u": 21,
25
+ "v": 22,
26
+ "w": 23,
27
+ "x": 24,
28
+ "y": 25,
29
+ "z": 26,
30
+ "|": 0,
31
+ "à": 27,
32
+ "á": 28,
33
+ "â": 29,
34
+ "ã": 30,
35
+ "è": 31,
36
+ "é": 32,
37
+ "ê": 33,
38
+ "ì": 34,
39
+ "í": 35,
40
+ "ò": 36,
41
+ "ó": 37,
42
+ "ô": 38,
43
+ "õ": 39,
44
+ "ù": 40,
45
+ "ú": 41,
46
+ "ý": 42,
47
+ "ă": 43,
48
+ "đ": 44,
49
+ "ĩ": 45,
50
+ "ũ": 46,
51
+ "ơ": 47,
52
+ "ư": 48,
53
+ "ạ": 49,
54
+ "ả": 50,
55
+ "ấ": 51,
56
+ "ầ": 52,
57
+ "ẩ": 53,
58
+ "ẫ": 54,
59
+ "ậ": 55,
60
+ "ắ": 56,
61
+ "ằ": 57,
62
+ "ẳ": 58,
63
+ "ẵ": 59,
64
+ "ặ": 60,
65
+ "ẹ": 61,
66
+ "ẻ": 62,
67
+ "ẽ": 63,
68
+ "ế": 64,
69
+ "ề": 65,
70
+ "ể": 66,
71
+ "ễ": 67,
72
+ "ệ": 68,
73
+ "ỉ": 69,
74
+ "ị": 70,
75
+ "ọ": 71,
76
+ "ỏ": 72,
77
+ "ố": 73,
78
+ "ồ": 74,
79
+ "ổ": 75,
80
+ "ỗ": 76,
81
+ "ộ": 77,
82
+ "ớ": 78,
83
+ "ờ": 79,
84
+ "ở": 80,
85
+ "ỡ": 81,
86
+ "ợ": 82,
87
+ "ụ": 83,
88
+ "ủ": 84,
89
+ "ứ": 85,
90
+ "ừ": 86,
91
+ "ử": 87,
92
+ "ữ": 88,
93
+ "ự": 89,
94
+ "ỳ": 90,
95
+ "ỵ": 91,
96
+ "ỷ": 92,
97
+ "ỹ": 93
98
+ }