Hugging Face's logo

Cafet
/
w2v-bert-2.0-mongolian-colab-CV16.1_and_Fleur

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Model card Files
xet
Metrics Community
Cafet commited on
Commit
a188cca
·
verified ·
1 Parent(s): 0ffeb1b

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -5
  3. vocab.json +39 -66
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 68,
3
- "<s>": 67
4
  }
 
1
  {
2
+ "</s>": 41,
3
+ "<s>": 40
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "65": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "66": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "67": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "68": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
@@ -39,7 +39,6 @@
39
  "eos_token": "</s>",
40
  "model_max_length": 1000000000000000019884624838656,
41
  "pad_token": "[PAD]",
42
- "processor_class": "Wav2Vec2BertProcessor",
43
  "replace_word_delimiter_char": " ",
44
  "target_lang": null,
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
1
  {
2
  "added_tokens_decoder": {
3
+ "38": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "39": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "40": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "41": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
39
  "eos_token": "</s>",
40
  "model_max_length": 1000000000000000019884624838656,
41
  "pad_token": "[PAD]",
 
42
  "replace_word_delimiter_char": " ",
43
  "target_lang": null,
44
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
vocab.json CHANGED
@@ -1,69 +1,42 @@
1
  {
2
- "!": 1,
3
- "\"": 2,
4
- "%": 3,
5
- "&": 4,
6
- "'": 5,
7
- "+": 6,
8
- ",": 7,
9
- "-": 8,
10
- ".": 9,
11
- "/": 10,
12
- ":": 11,
13
- ";": 12,
14
- "?": 13,
15
- "[": 14,
16
- "[PAD]": 66,
17
- "[UNK]": 65,
18
- "]": 15,
19
  "|": 0,
20
- "~": 16,
21
- " ": 17,
22
- "«": 18,
23
- "²": 19,
24
- "»": 20,
25
- "½": 21,
26
- "¾": 22,
27
- "õ": 23,
28
- "а": 24,
29
- "б": 25,
30
- "в": 26,
31
- "г": 27,
32
- "д": 28,
33
- "е": 29,
34
- "ж": 30,
35
- "з": 31,
36
- "и": 32,
37
- "й": 33,
38
- "к": 34,
39
- "л": 35,
40
- "м": 36,
41
- "н": 37,
42
- "о": 38,
43
- "п": 39,
44
- "р": 40,
45
- "с": 41,
46
- "т": 42,
47
- "у": 43,
48
- "ф": 44,
49
- "х": 45,
50
- "ц": 46,
51
- "ч": 47,
52
- "ш": 48,
53
- "щ": 49,
54
- "ъ": 50,
55
- "ы": 51,
56
- "ь": 52,
57
- "э": 53,
58
- "ю": 54,
59
- "я": 55,
60
- "ё": 56,
61
- "ү": 57,
62
- "ө": 58,
63
- "​": 59,
64
- "–": 60,
65
- "‘": 61,
66
- "’": 62,
67
- "“": 63,
68
- "”": 64
69
  }
 
1
  {
2
+ "[": 1,
3
+ "[PAD]": 39,
4
+ "[UNK]": 38,
5
+ "]": 2,
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "|": 0,
7
+ "а": 3,
8
+ "б": 4,
9
+ "в": 5,
10
+ "г": 6,
11
+ "д": 7,
12
+ "е": 8,
13
+ "ж": 9,
14
+ "з": 10,
15
+ "и": 11,
16
+ "й": 12,
17
+ "к": 13,
18
+ "л": 14,
19
+ "м": 15,
20
+ "н": 16,
21
+ "о": 17,
22
+ "п": 18,
23
+ "р": 19,
24
+ "с": 20,
25
+ "т": 21,
26
+ "у": 22,
27
+ "ф": 23,
28
+ "х": 24,
29
+ "ц": 25,
30
+ "ч": 26,
31
+ "ш": 27,
32
+ "щ": 28,
33
+ "ъ": 29,
34
+ "ы": 30,
35
+ "ь": 31,
36
+ "э": 32,
37
+ "ю": 33,
38
+ "я": 34,
39
+ "ё": 35,
40
+ "ү": 36,
41
+ "ө": 37
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  }