Hugging Face's logo

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

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
ylacombe commited on
Commit
2576487
·
verified ·
1 Parent(s): e511138

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -5
  3. vocab.json +72 -36
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 38,
3
- "<s>": 37
4
  }
 
1
  {
2
+ "</s>": 74,
3
+ "<s>": 73
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "35": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "36": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "37": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "38": {
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
+ "71": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "72": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "73": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "74": {
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
@@ -1,39 +1,75 @@
1
  {
2
- "[PAD]": 36,
3
- "[UNK]": 35,
 
 
 
 
4
  "|": 0,
5
- "а": 1,
6
- "б": 2,
7
- "в": 3,
8
- "г": 4,
9
- "д": 5,
10
- "е": 6,
11
- "ж": 7,
12
- "з": 8,
13
- "и": 9,
14
- "й": 10,
15
- "к": 11,
16
- "л": 12,
17
- "м": 13,
18
- "н": 14,
19
- "о": 15,
20
- "п": 16,
21
- "р": 17,
22
- "с": 18,
23
- "т": 19,
24
- "у": 20,
25
- "ф": 21,
26
- "х": 22,
27
- "ц": 23,
28
- "ч": 24,
29
- "ш": 25,
30
- "ъ": 26,
31
- "ы": 27,
32
- "ь": 28,
33
- "э": 29,
34
- "ю": 30,
35
- "я": 31,
36
- "ё": 32,
37
- "ү": 33,
38
- "ө": 34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  }
 
1
  {
2
+ "B": 1,
3
+ "C": 2,
4
+ "E": 3,
5
+ "H": 4,
6
+ "[PAD]": 72,
7
+ "[UNK]": 71,
8
  "|": 0,
9
+ "Ё": 5,
10
+ "А": 6,
11
+ "Б": 7,
12
+ "В": 8,
13
+ "Г": 9,
14
+ "Д": 10,
15
+ "Е": 11,
16
+ "Ж": 12,
17
+ "З": 13,
18
+ "И": 14,
19
+ "Й": 15,
20
+ "К": 16,
21
+ "Л": 17,
22
+ "М": 18,
23
+ "Н": 19,
24
+ "О": 20,
25
+ "П": 21,
26
+ "Р": 22,
27
+ "С": 23,
28
+ "Т": 24,
29
+ "У": 25,
30
+ "Ф": 26,
31
+ "Х": 27,
32
+ "Ц": 28,
33
+ "Ч": 29,
34
+ "Ш": 30,
35
+ "Ь": 31,
36
+ "Э": 32,
37
+ "Ю": 33,
38
+ "Я": 34,
39
+ "а": 35,
40
+ "б": 36,
41
+ "в": 37,
42
+ "г": 38,
43
+ "д": 39,
44
+ "е": 40,
45
+ "ж": 41,
46
+ "з": 42,
47
+ "и": 43,
48
+ "й": 44,
49
+ "к": 45,
50
+ "л": 46,
51
+ "м": 47,
52
+ "н": 48,
53
+ "о": 49,
54
+ "п": 50,
55
+ "р": 51,
56
+ "с": 52,
57
+ "т": 53,
58
+ "у": 54,
59
+ "ф": 55,
60
+ "х": 56,
61
+ "ц": 57,
62
+ "ч": 58,
63
+ "ш": 59,
64
+ "ъ": 60,
65
+ "ы": 61,
66
+ "ь": 62,
67
+ "э": 63,
68
+ "ю": 64,
69
+ "я": 65,
70
+ "ё": 66,
71
+ "Ү": 67,
72
+ "ү": 68,
73
+ "Ө": 69,
74
+ "ө": 70
75
  }