Hugging Face's logo

shishirml
/
wav2vec2-large-xls-r-300m-Nepali_ShishirAI

Model card Files Community
shishirml commited on
Commit
8d989bd
•
1 Parent(s): 25cf01d

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