Hugging Face's logo

nbaden
/
wav2vec2-large-xlsr-53-demo-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
rebort commited on
Commit
f96ee50
•
1 Parent(s): 22b0346

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +3 -1
  2. tokenizer_config.json +4 -2
  3. vocab.json +46 -46
added_tokens.json CHANGED
@@ -1,4 +1,6 @@
1
  {
2
  "</s>": 49,
3
- "<s>": 48
 
 
4
  }
 
1
  {
2
  "</s>": 49,
3
+ "<s>": 48,
4
+ "[PAD]": 47,
5
+ "[UNK]": 46
6
  }
tokenizer_config.json CHANGED
@@ -19,7 +19,7 @@
19
  "48": {
20
  "content": "<s>",
21
  "lstrip": false,
22
- "normalized": true,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
@@ -27,12 +27,13 @@
27
  "49": {
28
  "content": "</s>",
29
  "lstrip": false,
30
- "normalized": true,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  }
35
  },
 
36
  "bos_token": "<s>",
37
  "clean_up_tokenization_spaces": true,
38
  "do_lower_case": false,
@@ -42,6 +43,7 @@
42
  "replace_word_delimiter_char": " ",
43
  "target_lang": null,
44
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
45
  "unk_token": "[UNK]",
46
  "word_delimiter_token": "|"
47
  }
 
19
  "48": {
20
  "content": "<s>",
21
  "lstrip": false,
22
+ "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
 
27
  "49": {
28
  "content": "</s>",
29
  "lstrip": false,
30
+ "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  }
35
  },
36
+ "additional_special_tokens": [],
37
  "bos_token": "<s>",
38
  "clean_up_tokenization_spaces": true,
39
  "do_lower_case": false,
 
43
  "replace_word_delimiter_char": " ",
44
  "target_lang": null,
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "tokenizer_file": null,
47
  "unk_token": "[UNK]",
48
  "word_delimiter_token": "|"
49
  }
vocab.json CHANGED
@@ -1,50 +1,50 @@
1
  {
2
  "[PAD]": 47,
3
  "[UNK]": 46,
4
- "c": 14,
5
- "i": 42,
6
- "o": 32,
7
- "y": 8,
8
- "|": 39,
9
- "«": 22,
10
- "»": 16,
11
- "а": 9,
12
- "б": 10,
13
- "в": 6,
14
- "г": 11,
15
- "д": 26,
16
- "е": 1,
17
- "ж": 31,
18
- "з": 33,
19
- "и": 12,
20
- "й": 2,
21
- "к": 18,
22
- "л": 24,
23
- "м": 40,
24
- "н": 4,
25
- "о": 7,
26
- "п": 38,
27
- "р": 23,
28
- "с": 43,
29
- "т": 17,
30
- "у": 44,
31
- "ф": 30,
32
- "х": 19,
33
- "ц": 29,
34
- "ч": 28,
35
- "ш": 5,
36
- "щ": 45,
37
- "ъ": 21,
38
- "ы": 25,
39
- "ь": 27,
40
- "э": 20,
41
- "ю": 34,
42
- "я": 3,
43
- "і": 35,
44
- "ј": 41,
45
- "ҕ": 36,
46
- "ҥ": 13,
47
- "ү": 15,
48
- "һ": 37,
49
- "ө": 0
50
  }
 
1
  {
2
  "[PAD]": 47,
3
  "[UNK]": 46,
4
+ "c": 21,
5
+ "i": 33,
6
+ "o": 13,
7
+ "y": 1,
8
+ "|": 23,
9
+ "«": 12,
10
+ "»": 8,
11
+ "а": 29,
12
+ "б": 18,
13
+ "в": 42,
14
+ "г": 16,
15
+ "д": 3,
16
+ "е": 20,
17
+ "ж": 28,
18
+ "з": 4,
19
+ "и": 14,
20
+ "й": 10,
21
+ "к": 22,
22
+ "л": 27,
23
+ "м": 19,
24
+ "н": 38,
25
+ "о": 41,
26
+ "п": 15,
27
+ "р": 31,
28
+ "с": 24,
29
+ "т": 6,
30
+ "у": 30,
31
+ "ф": 34,
32
+ "х": 36,
33
+ "ц": 35,
34
+ "ч": 45,
35
+ "ш": 25,
36
+ "щ": 26,
37
+ "ъ": 9,
38
+ "ы": 5,
39
+ "ь": 7,
40
+ "э": 43,
41
+ "ю": 39,
42
+ "я": 37,
43
+ "і": 32,
44
+ "ј": 17,
45
+ "ҕ": 0,
46
+ "ҥ": 2,
47
+ "ү": 40,
48
+ "һ": 44,
49
+ "ө": 11
50
  }