Hugging Face's logo

HuyenNguyen
/
w2v-bert-2.0-mongolian-colab-CV16.0

Transformers
Inference Endpoints
Model card Files Community
HuyenNguyen commited on
Commit
7cd2450
•
1 Parent(s): 36968e4

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +2 -3
  3. vocab.json +95 -69
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 71,
3
- "[PAD]": 70
4
  }
 
1
  {
2
+ "</s>": 97,
3
+ "[PAD]": 96
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "70": {
4
  "content": "[PAD]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "71": {
12
  "content": "</s>",
13
  "lstrip": false,
14
  "normalized": false,
@@ -23,7 +23,6 @@
23
  "eos_token": "</s>",
24
  "model_max_length": 1000000000000000019884624838656,
25
  "pad_token": "[PAD]",
26
- "processor_class": "Wav2Vec2BertProcessor",
27
  "replace_word_delimiter_char": " ",
28
  "target_lang": null,
29
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
1
  {
2
  "added_tokens_decoder": {
3
+ "96": {
4
  "content": "[PAD]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "97": {
12
  "content": "</s>",
13
  "lstrip": false,
14
  "normalized": false,
 
23
  "eos_token": "</s>",
24
  "model_max_length": 1000000000000000019884624838656,
25
  "pad_token": "[PAD]",
 
26
  "replace_word_delimiter_char": " ",
27
  "target_lang": null,
28
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
vocab.json CHANGED
@@ -1,72 +1,98 @@
1
  {
2
- "[PAD]": 70,
3
- "[UNK]": 70,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "|": 0,
5
- "à": 1,
6
- "á": 2,
7
- "â": 3,
8
- "ã": 4,
9
- "è": 5,
10
- "é": 6,
11
- "ê": 7,
12
- "ì": 8,
13
- "í": 9,
14
- "ò": 10,
15
- "ó": 11,
16
- "ô": 12,
17
- "õ": 13,
18
- "ù": 14,
19
- "ú": 15,
20
- "ý": 16,
21
- "ă": 17,
22
- "đ": 18,
23
- "ĩ": 19,
24
- "ũ": 20,
25
- "ơ": 21,
26
- "ư": 22,
27
- "ạ": 23,
28
- "ả": 24,
29
- "ấ": 25,
30
- "ầ": 26,
31
- "ẩ": 27,
32
- "ẫ": 28,
33
- "ậ": 29,
34
- "ắ": 30,
35
- "ằ": 31,
36
- "ẳ": 32,
37
- "ẵ": 33,
38
- "ặ": 34,
39
- "ẹ": 35,
40
- "ẻ": 36,
41
- "ẽ": 37,
42
- "ế": 38,
43
- "ề": 39,
44
- "ể": 40,
45
- "ễ": 41,
46
- "ệ": 42,
47
- "ỉ": 43,
48
- "ị": 44,
49
- "ọ": 45,
50
- "ỏ": 46,
51
- "ố": 47,
52
- "ồ": 48,
53
- "ổ": 49,
54
- "ỗ": 50,
55
- "ộ": 51,
56
- "ớ": 52,
57
- "ờ": 53,
58
- "ở": 54,
59
- "ỡ": 55,
60
- "ợ": 56,
61
- "ụ": 57,
62
- "ủ": 58,
63
- "ứ": 59,
64
- "ừ": 60,
65
- "ử": 61,
66
- "ữ": 62,
67
- "ự": 63,
68
- "ỳ": 64,
69
- "ỵ": 65,
70
- "ỷ": 66,
71
- "ỹ": 67
72
  }
 
1
  {
2
+ "[PAD]": 96,
3
+ "[UNK]": 96,
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
  }