shivamtiwari2112 commited on
Commit
e6472c0
1 Parent(s): 6ca5ab5

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 76,
3
+ "<s>": 75,
4
+ "[PAD]": 74
5
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "73": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "74": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "75": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "76": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
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 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "&": 1,
3
+ "[PAD]": 74,
4
+ "[UNK]": 73,
5
+ "|": 0,
6
+ "ँ": 3,
7
+ "ं": 4,
8
+ "ः": 5,
9
+ "अ": 6,
10
+ "आ": 7,
11
+ "इ": 8,
12
+ "ई": 9,
13
+ "उ": 10,
14
+ "ऊ": 11,
15
+ "ऋ": 12,
16
+ "ए": 13,
17
+ "ऐ": 14,
18
+ "ऑ": 15,
19
+ "ओ": 16,
20
+ "औ": 17,
21
+ "क": 18,
22
+ "ख": 19,
23
+ "ग": 20,
24
+ "घ": 21,
25
+ "च": 22,
26
+ "छ": 23,
27
+ "ज": 24,
28
+ "झ": 25,
29
+ "ञ": 26,
30
+ "ट": 27,
31
+ "ठ": 28,
32
+ "ड": 29,
33
+ "ढ": 30,
34
+ "ण": 31,
35
+ "त": 32,
36
+ "थ": 33,
37
+ "द": 34,
38
+ "ध": 35,
39
+ "न": 36,
40
+ "प": 37,
41
+ "फ": 38,
42
+ "ब": 39,
43
+ "भ": 40,
44
+ "म": 41,
45
+ "य": 42,
46
+ "र": 43,
47
+ "ल": 44,
48
+ "व": 45,
49
+ "श": 46,
50
+ "ष": 47,
51
+ "स": 48,
52
+ "ह": 49,
53
+ "़": 50,
54
+ "ा": 51,
55
+ "ि": 52,
56
+ "ी": 53,
57
+ "ु": 54,
58
+ "ू": 55,
59
+ "ृ": 56,
60
+ "ॅ": 57,
61
+ "े": 58,
62
+ "ै": 59,
63
+ "ॉ": 60,
64
+ "ो": 61,
65
+ "ौ": 62,
66
+ "्": 63,
67
+ "क़": 64,
68
+ "ख़": 65,
69
+ "ग़": 66,
70
+ "ज़": 67,
71
+ "ड़": 68,
72
+ "ढ़": 69,
73
+ "फ़": 70,
74
+ "।": 71,
75
+ "–": 72,
76
+ "’": 73
77
+ }