Hugging Face's logo

nguyenvulebinh
/
wav2vec2-base-vi

Transformers
PyTorch
Vietnamese
wav2vec2
pretraining
speech
Inference Endpoints
Model card Files Community
1
nguyenvulebinh commited on
Commit
8390f03
•
1 Parent(s): 2a37532

Upload processor

Browse files
Files changed (5) hide show
  1. added_tokens.json +4 -0
  2. preprocessor_config.json +10 -0
  3. special_tokens_map.json +134 -0
  4. tokenizer_config.json +14 -0
  5. vocab.json +98 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 97,
3
+ "<s>": 96
4
+ }
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
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
131
+ "eos_token": "</s>",
132
+ "pad_token": "<pad>",
133
+ "unk_token": "<unk>"
134
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "name_or_path": "./model-bin/wav2vec_pretrained/base/",
6
+ "pad_token": "<pad>",
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "replace_word_delimiter_char": " ",
9
+ "special_tokens_map_file": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "tokenizer_file": null,
12
+ "unk_token": "<unk>",
13
+ "word_delimiter_token": "|"
14
+ }
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
+ }