Hugging Face's logo

rdzotz
/
w2v-bert-2.0-russian-colab-CV16.0

Transformers
Inference Endpoints
Model card Files Community
rdzotz commited on
Commit
8d14889
•
1 Parent(s): a62e841

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -5
  3. vocab.json +35 -43
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 45,
3
- "<s>": 44
4
  }
 
1
  {
2
+ "</s>": 37,
3
+ "<s>": 36
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "42": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "43": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "44": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "45": {
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
+ "34": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "35": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "36": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "37": {
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
@@ -1,46 +1,38 @@
1
  {
2
- "(": 1,
3
- ")": 2,
4
- "[PAD]": 43,
5
- "[UNK]": 42,
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
- "‑": 36,
41
- "–": 37,
42
- "—": 38,
43
- "„": 39,
44
- "…": 40,
45
- "−": 41
46
  }
 
1
  {
2
+ "[PAD]": 35,
3
+ "[UNK]": 34,
 
 
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
+ "щ": 26,
31
+ "ъ": 27,
32
+ "ы": 28,
33
+ "ь": 29,
34
+ "э": 30,
35
+ "ю": 31,
36
+ "я": 32,
37
+ "ё": 33
 
 
 
 
 
 
38
  }