Hugging Face's logo

shivamtiwari2112
/
wav2vec2-large-xlsr-hindi

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
shivamtiwari2112 commited on
Commit
f1594a9
•
1 Parent(s): fa88c68

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +5 -0
  2. special_tokens_map.json +6 -0
  3. tokenizer_config.json +48 -0
  4. vocab.json +104 -0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 103,
3
+ "<s>": 102,
4
+ "[PAD]": 101
5
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "100": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "101": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "102": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "103": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "processor_class": "Wav2Vec2Processor",
43
+ "replace_word_delimiter_char": " ",
44
+ "target_lang": null,
45
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "unk_token": "[UNK]",
47
+ "word_delimiter_token": "|"
48
+ }
vocab.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "&": 17,
3
+ "'": 0,
4
+ "[PAD]": 101,
5
+ "[UNK]": 100,
6
+ "a": 24,
7
+ "b": 46,
8
+ "c": 1,
9
+ "d": 34,
10
+ "e": 96,
11
+ "f": 36,
12
+ "g": 18,
13
+ "h": 23,
14
+ "i": 85,
15
+ "j": 51,
16
+ "k": 82,
17
+ "l": 16,
18
+ "m": 81,
19
+ "n": 74,
20
+ "o": 77,
21
+ "p": 22,
22
+ "q": 61,
23
+ "r": 83,
24
+ "s": 27,
25
+ "t": 66,
26
+ "u": 47,
27
+ "v": 72,
28
+ "w": 43,
29
+ "x": 21,
30
+ "y": 26,
31
+ "z": 41,
32
+ "|": 29,
33
+ "ँ": 67,
34
+ "ं": 58,
35
+ "ः": 99,
36
+ "अ": 94,
37
+ "आ": 15,
38
+ "इ": 38,
39
+ "ई": 62,
40
+ "उ": 98,
41
+ "ऊ": 7,
42
+ "ऋ": 71,
43
+ "ए": 90,
44
+ "ऐ": 60,
45
+ "ऑ": 95,
46
+ "ओ": 79,
47
+ "औ": 93,
48
+ "क": 78,
49
+ "ख": 92,
50
+ "ग": 9,
51
+ "घ": 88,
52
+ "च": 40,
53
+ "छ": 55,
54
+ "ज": 68,
55
+ "झ": 57,
56
+ "ञ": 73,
57
+ "ट": 86,
58
+ "ठ": 39,
59
+ "ड": 2,
60
+ "ढ": 89,
61
+ "ण": 44,
62
+ "त": 6,
63
+ "थ": 3,
64
+ "द": 48,
65
+ "ध": 49,
66
+ "न": 8,
67
+ "प": 14,
68
+ "फ": 56,
69
+ "ब": 33,
70
+ "भ": 97,
71
+ "म": 11,
72
+ "य": 52,
73
+ "र": 4,
74
+ "ल": 12,
75
+ "व": 91,
76
+ "श": 84,
77
+ "ष": 76,
78
+ "स": 28,
79
+ "ह": 20,
80
+ "़": 31,
81
+ "ा": 65,
82
+ "ि": 75,
83
+ "ी": 50,
84
+ "ु": 59,
85
+ "ू": 10,
86
+ "ृ": 32,
87
+ "ॅ": 19,
88
+ "े": 37,
89
+ "ै": 30,
90
+ "ॉ": 13,
91
+ "ो": 80,
92
+ "ौ": 5,
93
+ "्": 87,
94
+ "क़": 54,
95
+ "ख़": 70,
96
+ "ग़": 42,
97
+ "ज़": 63,
98
+ "ड़": 35,
99
+ "ढ़": 45,
100
+ "फ़": 69,
101
+ "।": 100,
102
+ "–": 25,
103
+ "’": 53
104
+ }