Hugging Face's logo

Anujgr8
/
indic-bert-large-cs

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Model card Files
xet
Metrics Community
Anujgr8 commited on
Commit
4126121
·
verified ·
1 Parent(s): 824e7cc

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +30 -0
  3. tokenizer_config.json +47 -0
  4. vocab.json +97 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 96,
3
+ "<s>": 95
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "93": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "94": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "95": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "96": {
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,
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",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ ":": 1,
3
+ "[PAD]": 94,
4
+ "[UNK]": 93,
5
+ "a": 2,
6
+ "b": 3,
7
+ "c": 4,
8
+ "d": 5,
9
+ "e": 6,
10
+ "f": 7,
11
+ "g": 8,
12
+ "h": 9,
13
+ "i": 10,
14
+ "j": 11,
15
+ "k": 12,
16
+ "l": 13,
17
+ "m": 14,
18
+ "n": 15,
19
+ "o": 16,
20
+ "p": 17,
21
+ "q": 18,
22
+ "r": 19,
23
+ "s": 20,
24
+ "t": 21,
25
+ "u": 22,
26
+ "v": 23,
27
+ "w": 24,
28
+ "x": 25,
29
+ "y": 26,
30
+ "z": 27,
31
+ "|": 0,
32
+ "ँ": 28,
33
+ "ं": 29,
34
+ "ः": 30,
35
+ "अ": 31,
36
+ "आ": 32,
37
+ "इ": 33,
38
+ "ई": 34,
39
+ "उ": 35,
40
+ "ऊ": 36,
41
+ "ए": 37,
42
+ "ऐ": 38,
43
+ "ऑ": 39,
44
+ "ओ": 40,
45
+ "औ": 41,
46
+ "क": 42,
47
+ "ख": 43,
48
+ "ग": 44,
49
+ "घ": 45,
50
+ "च": 46,
51
+ "छ": 47,
52
+ "ज": 48,
53
+ "झ": 49,
54
+ "ञ": 50,
55
+ "ट": 51,
56
+ "ठ": 52,
57
+ "ड": 53,
58
+ "ढ": 54,
59
+ "ण": 55,
60
+ "त": 56,
61
+ "थ": 57,
62
+ "द": 58,
63
+ "ध": 59,
64
+ "न": 60,
65
+ "प": 61,
66
+ "फ": 62,
67
+ "ब": 63,
68
+ "भ": 64,
69
+ "म": 65,
70
+ "य": 66,
71
+ "र": 67,
72
+ "ल": 68,
73
+ "व": 69,
74
+ "श": 70,
75
+ "ष": 71,
76
+ "स": 72,
77
+ "ह": 73,
78
+ "़": 74,
79
+ "ा": 75,
80
+ "ि": 76,
81
+ "ी": 77,
82
+ "ु": 78,
83
+ "ू": 79,
84
+ "ृ": 80,
85
+ "े": 81,
86
+ "ै": 82,
87
+ "ॉ": 83,
88
+ "ो": 84,
89
+ "ौ": 85,
90
+ "्": 86,
91
+ "ख़": 87,
92
+ "ज़": 88,
93
+ "ड़": 89,
94
+ "ढ़": 90,
95
+ "fi": 91,
96
+ "fl": 92
97
+ }