eventhorizon28 commited on
Commit
a41ba4c
1 Parent(s): 3035cd6

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>": 73
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": {
3
+ "content": "ङ",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "unk_token": {
10
+ "content": "<unk>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_blank": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "ङ",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "73": {
13
+ "content": "<unk>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "clean_up_tokenization_spaces": true,
22
+ "is_uroman": false,
23
+ "language": "mar",
24
+ "model_max_length": 1000000000000000019884624838656,
25
+ "normalize": true,
26
+ "pad_token": "ङ",
27
+ "phonemize": false,
28
+ "tokenizer_class": "VitsTokenizer",
29
+ "unk_token": "<unk>",
30
+ "verbose": false
31
+ }
vocab.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 29,
3
+ "'": 59,
4
+ "-": 19,
5
+ "0": 41,
6
+ "1": 13,
7
+ "2": 6,
8
+ "4": 42,
9
+ "6": 44,
10
+ "7": 35,
11
+ "9": 34,
12
+ "_": 10,
13
+ "ʇ": 65,
14
+ "ʈ": 26,
15
+ "ं": 7,
16
+ "ः": 45,
17
+ "अ": 60,
18
+ "आ": 2,
19
+ "इ": 61,
20
+ "ई": 20,
21
+ "उ": 51,
22
+ "ऊ": 12,
23
+ "ऋ": 40,
24
+ "ए": 31,
25
+ "ऐ": 27,
26
+ "ओ": 18,
27
+ "औ": 15,
28
+ "क": 14,
29
+ "ख": 5,
30
+ "ग": 24,
31
+ "घ": 67,
32
+ "ङ": 0,
33
+ "च": 17,
34
+ "छ": 55,
35
+ "ज": 22,
36
+ "झ": 25,
37
+ "ञ": 49,
38
+ "ट": 9,
39
+ "ठ": 36,
40
+ "ड": 30,
41
+ "ढ": 4,
42
+ "ण": 58,
43
+ "त": 8,
44
+ "थ": 72,
45
+ "द": 28,
46
+ "ध": 47,
47
+ "न": 52,
48
+ "प": 48,
49
+ "फ": 50,
50
+ "ब": 3,
51
+ "भ": 70,
52
+ "म": 54,
53
+ "य": 43,
54
+ "र": 69,
55
+ "ऱ": 37,
56
+ "ल": 46,
57
+ "ळ": 16,
58
+ "ऴ": 66,
59
+ "व": 38,
60
+ "श": 21,
61
+ "ष": 53,
62
+ "स": 11,
63
+ "ह": 1,
64
+ "ा": 62,
65
+ "ि": 57,
66
+ "ी": 71,
67
+ "ु": 63,
68
+ "ू": 64,
69
+ "ृ": 23,
70
+ "े": 56,
71
+ "ै": 32,
72
+ "ो": 39,
73
+ "ौ": 33,
74
+ "्": 68
75
+ }