Hugging Face's logo

amankhandelia
/
wav2vec2-large-mms-1b-hindi-colab

Model card Files Community
amankhandelia commited on
Commit
4e09d60
·
1 Parent(s): f7e99eb

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +22 -0
  3. tokenizer_config.json +13 -0
  4. vocab.json +117 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 114,
3
+ "<s>": 113
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": "hin",
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "hin": {
3
+ "#": 0,
4
+ "0": 1,
5
+ "1": 2,
6
+ "2": 3,
7
+ "3": 4,
8
+ "4": 5,
9
+ "5": 6,
10
+ "6": 7,
11
+ "7": 8,
12
+ "8": 9,
13
+ "9": 10,
14
+ "[PAD]": 112,
15
+ "[UNK]": 111,
16
+ "a": 11,
17
+ "b": 12,
18
+ "c": 13,
19
+ "d": 14,
20
+ "e": 15,
21
+ "f": 16,
22
+ "g": 17,
23
+ "h": 18,
24
+ "i": 19,
25
+ "j": 20,
26
+ "k": 21,
27
+ "l": 22,
28
+ "m": 23,
29
+ "n": 24,
30
+ "o": 25,
31
+ "p": 26,
32
+ "q": 27,
33
+ "r": 28,
34
+ "s": 29,
35
+ "t": 30,
36
+ "u": 31,
37
+ "v": 32,
38
+ "w": 33,
39
+ "x": 34,
40
+ "y": 35,
41
+ "z": 36,
42
+ "ö": 37,
43
+ "ँ": 38,
44
+ "ं": 39,
45
+ "ः": 40,
46
+ "अ": 41,
47
+ "आ": 42,
48
+ "इ": 43,
49
+ "ई": 44,
50
+ "उ": 45,
51
+ "ऊ": 46,
52
+ "ऋ": 47,
53
+ "ए": 48,
54
+ "ऐ": 49,
55
+ "ऑ": 50,
56
+ "ओ": 51,
57
+ "औ": 52,
58
+ "क": 53,
59
+ "ख": 54,
60
+ "ग": 55,
61
+ "घ": 56,
62
+ "च": 57,
63
+ "छ": 58,
64
+ "ज": 59,
65
+ "झ": 60,
66
+ "ञ": 61,
67
+ "ट": 62,
68
+ "ठ": 63,
69
+ "ड": 64,
70
+ "ढ": 65,
71
+ "ण": 66,
72
+ "त": 67,
73
+ "थ": 68,
74
+ "द": 69,
75
+ "ध": 70,
76
+ "न": 71,
77
+ "प": 72,
78
+ "फ": 73,
79
+ "ब": 74,
80
+ "भ": 75,
81
+ "म": 76,
82
+ "य": 77,
83
+ "र": 78,
84
+ "ऱ": 79,
85
+ "ल": 80,
86
+ "व": 81,
87
+ "श": 82,
88
+ "ष": 83,
89
+ "स": 84,
90
+ "ह": 85,
91
+ "़": 86,
92
+ "ा": 87,
93
+ "ि": 88,
94
+ "ी": 89,
95
+ "ु": 90,
96
+ "ू": 91,
97
+ "ृ": 92,
98
+ "ॅ": 93,
99
+ "े": 94,
100
+ "ै": 95,
101
+ "ॉ": 96,
102
+ "ो": 97,
103
+ "ौ": 98,
104
+ "्": 99,
105
+ "ॐ": 100,
106
+ "क़": 101,
107
+ "ख़": 102,
108
+ "ग़": 103,
109
+ "ज़": 104,
110
+ "ड़": 105,
111
+ "ढ़": 106,
112
+ "फ़": 107,
113
+ "य़": 108,
114
+ "५": 109,
115
+ "७": 110
116
+ }
117
+ }