Hugging Face's logo

santoshpandey
/
indic-nepali-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files Metrics Community
santoshpandey commited on
Commit
aa202de
·
verified ·
1 Parent(s): dd821be

Upload tokenizer

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