Hugging Face's logo

Bajiyo
/
w2v-bert-2_7_datasets

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Generated from Trainer
Model card Files
xet
 Metrics Community
1
Bajiyo commited on
Commit
98b86d0
·
verified ·
1 Parent(s): 09f8924

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -5
  3. vocab.json +77 -97
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 99,
3
- "<s>": 98
4
  }
 
1
  {
2
+ "</s>": 79,
3
+ "<s>": 78
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "96": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "97": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "98": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "99": {
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
+ "76": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "77": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "78": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "79": {
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
@@ -1,100 +1,80 @@
1
  {
2
- "$": 1,
3
- "&": 2,
4
- "+": 3,
5
- "/": 4,
6
- "0": 5,
7
- "1": 6,
8
- "2": 7,
9
- "3": 8,
10
- "4": 9,
11
- "5": 10,
12
- "6": 11,
13
- "7": 12,
14
- "8": 13,
15
- "9": 14,
16
- "[": 15,
17
- "[PAD]": 97,
18
- "[UNK]": 96,
19
- "]": 16,
20
- "_": 17,
21
  "|": 0,
22
- "~": 18,
23
- "°": 19,
24
- "ം": 20,
25
- "ഃ": 21,
26
- "അ": 22,
27
- "ആ": 23,
28
- "ഇ": 24,
29
- "ഈ": 25,
30
- "ഉ": 26,
31
- "ഊ": 27,
32
- "ഋ": 28,
33
- "എ": 29,
34
- "ഏ": 30,
35
- "ഐ": 31,
36
- "ഒ": 32,
37
- "ഓ": 33,
38
- "ഔ": 34,
39
- "ക": 35,
40
- "ഖ": 36,
41
- "ഗ": 37,
42
- "ഘ": 38,
43
- "ങ": 39,
44
- "ച": 40,
45
- "ഛ": 41,
46
- "ജ": 42,
47
- "ഝ": 43,
48
- "ഞ": 44,
49
- "ട": 45,
50
- "ഠ": 46,
51
- "ഡ": 47,
52
- "ഢ": 48,
53
- "ണ": 49,
54
- "ത": 50,
55
- "ഥ": 51,
56
- "ദ": 52,
57
- "ധ": 53,
58
- "ന": 54,
59
- "പ": 55,
60
- "ഫ": 56,
61
- "ബ": 57,
62
- "ഭ": 58,
63
- "മ": 59,
64
- "യ": 60,
65
- "ര": 61,
66
- "റ": 62,
67
- "ല": 63,
68
- "ള": 64,
69
- "ഴ": 65,
70
- "വ": 66,
71
- "ശ": 67,
72
- "ഷ": 68,
73
- "സ": 69,
74
- "ഹ": 70,
75
- "ാ": 71,
76
- "ി": 72,
77
- "ീ": 73,
78
- "ു": 74,
79
- "ൂ": 75,
80
- "ൃ": 76,
81
- "െ": 77,
82
- "േ": 78,
83
- "ൈ": 79,
84
- "ൊ": 80,
85
- "ോ": 81,
86
- "ൌ": 82,
87
- "്": 83,
88
- "ൗ": 84,
89
- "൱": 85,
90
- "ൺ": 86,
91
- "ൻ": 87,
92
- "ർ": 88,
93
- "ൽ": 89,
94
- "ൾ": 90,
95
- "ൿ": 91,
96
- "‌": 92,
97
- "‍": 93,
98
- "–": 94,
99
- "’": 95
100
  }
 
1
  {
2
+ "[PAD]": 77,
3
+ "[UNK]": 76,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "|": 0,
5
+ "°": 1,
6
+ "ം": 2,
7
+ "ഃ": 3,
8
+ "അ": 4,
9
+ "ആ": 5,
10
+ "ഇ": 6,
11
+ "ഈ": 7,
12
+ "ഉ": 8,
13
+ "ഊ": 9,
14
+ "ഋ": 10,
15
+ "എ": 11,
16
+ "ഏ": 12,
17
+ "ഐ": 13,
18
+ "ഒ": 14,
19
+ "ഓ": 15,
20
+ "ഔ": 16,
21
+ "ക": 17,
22
+ "ഖ": 18,
23
+ "ഗ": 19,
24
+ "ഘ": 20,
25
+ "ങ": 21,
26
+ "ച": 22,
27
+ "ഛ": 23,
28
+ "ജ": 24,
29
+ "ഝ": 25,
30
+ "ഞ": 26,
31
+ "ട": 27,
32
+ "ഠ": 28,
33
+ "ഡ": 29,
34
+ "ഢ": 30,
35
+ "ണ": 31,
36
+ "ത": 32,
37
+ "ഥ": 33,
38
+ "ദ": 34,
39
+ "ധ": 35,
40
+ "ന": 36,
41
+ "പ": 37,
42
+ "ഫ": 38,
43
+ "ബ": 39,
44
+ "ഭ": 40,
45
+ "മ": 41,
46
+ "യ": 42,
47
+ "ര": 43,
48
+ "റ": 44,
49
+ "ല": 45,
50
+ "ള": 46,
51
+ "ഴ": 47,
52
+ "വ": 48,
53
+ "ശ": 49,
54
+ "ഷ": 50,
55
+ "സ": 51,
56
+ "ഹ": 52,
57
+ "ാ": 53,
58
+ "ി": 54,
59
+ "ീ": 55,
60
+ "ു": 56,
61
+ "ൂ": 57,
62
+ "ൃ": 58,
63
+ "െ": 59,
64
+ "േ": 60,
65
+ "ൈ": 61,
66
+ "ൊ": 62,
67
+ "ോ": 63,
68
+ "ൌ": 64,
69
+ "്": 65,
70
+ "ൗ": 66,
71
+ "൱": 67,
72
+ "ൺ": 68,
73
+ "ൻ": 69,
74
+ "ർ": 70,
75
+ "ൽ": 71,
76
+ "ൾ": 72,
77
+ "ൿ": 73,
78
+ "‌": 74,
79
+ "‍": 75
 
 
 
80
  }