shishirml commited on
Commit
576d57d
1 Parent(s): 10d70b1

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 96,
3
+ "<s>": 95
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": "npi",
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "npi": {
3
+ "[PAD]": 94,
4
+ "[UNK]": 93,
5
+ "\\": 1,
6
+ "a": 2,
7
+ "b": 3,
8
+ "c": 4,
9
+ "e": 5,
10
+ "f": 6,
11
+ "k": 7,
12
+ "o": 8,
13
+ "|": 0,
14
+ "ँ": 9,
15
+ "ं": 10,
16
+ "ः": 11,
17
+ "अ": 12,
18
+ "आ": 13,
19
+ "इ": 14,
20
+ "ई": 15,
21
+ "उ": 16,
22
+ "ऊ": 17,
23
+ "ऋ": 18,
24
+ "ए": 19,
25
+ "ऐ": 20,
26
+ "ऑ": 21,
27
+ "ओ": 22,
28
+ "औ": 23,
29
+ "क": 24,
30
+ "ख": 25,
31
+ "ग": 26,
32
+ "घ": 27,
33
+ "ङ": 28,
34
+ "च": 29,
35
+ "छ": 30,
36
+ "ज": 31,
37
+ "झ": 32,
38
+ "ञ": 33,
39
+ "ट": 34,
40
+ "ठ": 35,
41
+ "ड": 36,
42
+ "ढ": 37,
43
+ "ण": 38,
44
+ "त": 39,
45
+ "थ": 40,
46
+ "द": 41,
47
+ "ध": 42,
48
+ "न": 43,
49
+ "प": 44,
50
+ "फ": 45,
51
+ "ब": 46,
52
+ "भ": 47,
53
+ "म": 48,
54
+ "य": 49,
55
+ "र": 50,
56
+ "ऱ": 51,
57
+ "ल": 52,
58
+ "व": 53,
59
+ "श": 54,
60
+ "ष": 55,
61
+ "स": 56,
62
+ "ह": 57,
63
+ "़": 58,
64
+ "ा": 59,
65
+ "ि": 60,
66
+ "ी": 61,
67
+ "ु": 62,
68
+ "ू": 63,
69
+ "ृ": 64,
70
+ "े": 65,
71
+ "ै": 66,
72
+ "ॉ": 67,
73
+ "ॊ": 68,
74
+ "ो": 69,
75
+ "ौ": 70,
76
+ "्": 71,
77
+ "ॐ": 72,
78
+ "॑": 73,
79
+ "ॠ": 74,
80
+ "।": 75,
81
+ "०": 76,
82
+ "१": 77,
83
+ "२": 78,
84
+ "३": 79,
85
+ "४": 80,
86
+ "५": 81,
87
+ "६": 82,
88
+ "७": 83,
89
+ "८": 84,
90
+ "९": 85,
91
+ "॰": 86,
92
+ "​": 87,
93
+ "‌": 88,
94
+ "‍": 89,
95
+ "‎": 90,
96
+ "‏": 91,
97
+ " ": 92
98
+ }
99
+ }