SakshiRathi77 commited on
Commit
dc8490f
1 Parent(s): 332bac5

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 69,
3
+ "<s>": 68
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<s>",
19
+ "eos_token": "</s>",
20
+ "pad_token": "[PAD]",
21
+ "unk_token": "[UNK]"
22
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "target_lang": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 68,
3
+ "[UNK]": 67,
4
+ "|": 0,
5
+ "ँ": 2,
6
+ "ं": 3,
7
+ "ः": 4,
8
+ "अ": 5,
9
+ "आ": 6,
10
+ "इ": 7,
11
+ "ई": 8,
12
+ "उ": 9,
13
+ "ऊ": 10,
14
+ "ऋ": 11,
15
+ "ए": 12,
16
+ "ऐ": 13,
17
+ "ऑ": 14,
18
+ "ओ": 15,
19
+ "औ": 16,
20
+ "क": 17,
21
+ "ख": 18,
22
+ "ग": 19,
23
+ "घ": 20,
24
+ "च": 21,
25
+ "छ": 22,
26
+ "ज": 23,
27
+ "झ": 24,
28
+ "ञ": 25,
29
+ "ट": 26,
30
+ "ठ": 27,
31
+ "ड": 28,
32
+ "ढ": 29,
33
+ "ण": 30,
34
+ "त": 31,
35
+ "थ": 32,
36
+ "द": 33,
37
+ "ध": 34,
38
+ "न": 35,
39
+ "प": 36,
40
+ "फ": 37,
41
+ "ब": 38,
42
+ "भ": 39,
43
+ "म": 40,
44
+ "य": 41,
45
+ "र": 42,
46
+ "ल": 43,
47
+ "व": 44,
48
+ "श": 45,
49
+ "ष": 46,
50
+ "स": 47,
51
+ "ह": 48,
52
+ "़": 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
+ "क़": 63,
67
+ "ज़": 64,
68
+ "ड़": 65,
69
+ "ढ़": 66,
70
+ "फ़": 67
71
+ }