Hugging Face's logo

Hemantrao
/
wav2vec2-large-xls-r-300m-hindi_marathi-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Hemantrao commited on
Commit
0a72e4f
•
1 Parent(s): 097d1dc

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +93 -140
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 152,
3
- "<s>": 151
4
  }
 
1
  {
2
+ "</s>": 105,
3
+ "<s>": 104
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "149": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "150": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "151": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "152": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "102": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "103": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "104": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "105": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -10,144 +10,97 @@
10
  ":": 8,
11
  ";": 9,
12
  "?": 10,
13
- "A": 11,
14
- "B": 12,
15
- "C": 13,
16
- "D": 14,
17
- "E": 15,
18
- "F": 16,
19
- "G": 17,
20
- "H": 18,
21
- "I": 19,
22
- "J": 20,
23
- "K": 21,
24
- "L": 22,
25
- "M": 23,
26
- "N": 24,
27
- "O": 25,
28
- "P": 26,
29
- "R": 27,
30
- "S": 28,
31
- "T": 29,
32
- "V": 30,
33
- "W": 31,
34
- "X": 32,
35
- "Y": 33,
36
- "Z": 34,
37
- "[PAD]": 150,
38
- "[UNK]": 149,
39
- "a": 35,
40
- "b": 36,
41
- "c": 37,
42
- "d": 38,
43
- "e": 39,
44
- "f": 40,
45
- "g": 41,
46
- "h": 42,
47
- "i": 43,
48
- "j": 44,
49
- "k": 45,
50
- "l": 46,
51
- "m": 47,
52
- "n": 48,
53
- "o": 49,
54
- "p": 50,
55
- "q": 51,
56
- "r": 52,
57
- "s": 53,
58
- "t": 54,
59
- "u": 55,
60
- "v": 56,
61
- "w": 57,
62
- "x": 58,
63
- "y": 59,
64
- "z": 60,
65
- "|": 61,
66
- "ँ": 62,
67
- "ं": 63,
68
- "ः": 64,
69
- "अ": 65,
70
- "आ": 66,
71
- "इ": 67,
72
- "ई": 68,
73
- "उ": 69,
74
- "ऊ": 70,
75
- "ऋ": 71,
76
- "ऌ": 72,
77
- "ऍ": 73,
78
- "ऎ": 74,
79
- "ए": 75,
80
- "ऐ": 76,
81
- "ऑ": 77,
82
- "ओ": 78,
83
- "औ": 79,
84
- "क": 80,
85
- "ख": 81,
86
- "ग": 82,
87
- "घ": 83,
88
- "ङ": 84,
89
- "च": 85,
90
- "छ": 86,
91
- "ज": 87,
92
- "झ": 88,
93
- "ञ": 89,
94
- "ट": 90,
95
- "ठ": 91,
96
- "ड": 92,
97
- "ढ": 93,
98
- "ण": 94,
99
- "त": 95,
100
- "थ": 96,
101
- "द": 97,
102
- "ध": 98,
103
- "न": 99,
104
- "प": 100,
105
- "फ": 101,
106
- "ब": 102,
107
- "भ": 103,
108
- "म": 104,
109
- "य": 105,
110
- "र": 106,
111
- "ऱ": 107,
112
- "ल": 108,
113
- "ळ": 109,
114
- "व": 110,
115
- "श": 111,
116
- "ष": 112,
117
- "स": 113,
118
- "ह": 114,
119
- "़": 115,
120
- "ऽ": 116,
121
- "ा": 117,
122
- "ि": 118,
123
- "ी": 119,
124
- "ु": 120,
125
- "ू": 121,
126
- "ृ": 122,
127
- "ॄ": 123,
128
- "ॅ": 124,
129
- "ॆ": 125,
130
- "े": 126,
131
- "ै": 127,
132
- "ॉ": 128,
133
- "ॊ": 129,
134
- "ो": 130,
135
- "ौ": 131,
136
- "्": 132,
137
- "॓": 133,
138
- "॔": 134,
139
- "क़": 135,
140
- "ग़": 136,
141
- "ज़": 137,
142
- "ड़": 138,
143
- "ढ़": 139,
144
- "फ़": 140,
145
- "य़": 141,
146
- "।": 142,
147
- "॥": 143,
148
- "ॲ": 144,
149
- "‘": 145,
150
- "’": 146,
151
- "“": 147,
152
- "”": 148
153
  }
 
10
  ":": 8,
11
  ";": 9,
12
  "?": 10,
13
+ "[PAD]": 103,
14
+ "[UNK]": 102,
15
+ "|": 11,
16
+ "ँ": 12,
17
+ "ं": 13,
18
+ "ः": 14,
19
+ "अ": 15,
20
+ "आ": 16,
21
+ "इ": 17,
22
+ "ई": 18,
23
+ "उ": 19,
24
+ "ऊ": 20,
25
+ "ऋ": 21,
26
+ "ऌ": 22,
27
+ "ऍ": 23,
28
+ "ऎ": 24,
29
+ "ए": 25,
30
+ "ऐ": 26,
31
+ "ऑ": 27,
32
+ "ओ": 28,
33
+ "औ": 29,
34
+ "क": 30,
35
+ "ख": 31,
36
+ "ग": 32,
37
+ "घ": 33,
38
+ "ङ": 34,
39
+ "च": 35,
40
+ "छ": 36,
41
+ "ज": 37,
42
+ "झ": 38,
43
+ "ञ": 39,
44
+ "ट": 40,
45
+ "ठ": 41,
46
+ "ड": 42,
47
+ "ढ": 43,
48
+ "ण": 44,
49
+ "त": 45,
50
+ "थ": 46,
51
+ "द": 47,
52
+ "ध": 48,
53
+ "न": 49,
54
+ "प": 50,
55
+ "फ": 51,
56
+ "ब": 52,
57
+ "भ": 53,
58
+ "म": 54,
59
+ "य": 55,
60
+ "र": 56,
61
+ "ऱ": 57,
62
+ "ल": 58,
63
+ "ळ": 59,
64
+ "व": 60,
65
+ "श": 61,
66
+ "ष": 62,
67
+ "स": 63,
68
+ "ह": 64,
69
+ "़": 65,
70
+ "ऽ": 66,
71
+ "ा": 67,
72
+ "ि": 68,
73
+ "ी": 69,
74
+ "ु": 70,
75
+ "ू": 71,
76
+ "ृ": 72,
77
+ "ॄ": 73,
78
+ "ॅ": 74,
79
+ "ॆ": 75,
80
+ "े": 76,
81
+ "ै": 77,
82
+ "ॉ": 78,
83
+ "ॊ": 79,
84
+ "ो": 80,
85
+ "ौ": 81,
86
+ "्": 82,
87
+ "॓": 83,
88
+ "॔": 84,
89
+ "क़": 85,
90
+ "ख़": 86,
91
+ "ग़": 87,
92
+ "ज़": 88,
93
+ "ड़": 89,
94
+ "ढ़": 90,
95
+ "फ़": 91,
96
+ "य़": 92,
97
+ "ॢ": 93,
98
+ "।": 94,
99
+ "॥": 95,
100
+ "ॲ": 96,
101
+ "–": 97,
102
+ "‘": 98,
103
+ "’": 99,
104
+ "“": 100,
105
+ "”": 101
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
106
  }