Hugging Face's logo

TheAIchemist13
/
hindi_wav2vec2_optimized

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files
xet
Community
1
TheAIchemist13 commited on
Commit
c6d9248
·
1 Parent(s): 74a4723

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -4
  2. special_tokens_map.json +2 -2
  3. tokenizer_config.json +16 -16
  4. vocab.json +90 -67
added_tokens.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "</s>": 2,
3
- "<pad>": 1,
4
- "<s>": 0,
5
- "<unk>": 3
6
  }
 
1
  {
2
+ "</s>": 91,
3
+ "<s>": 90,
4
+ "[PAD]": 89,
5
+ "[UNK]": 88
6
  }
special_tokens_map.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "bos_token": "<s>",
3
  "eos_token": "</s>",
4
- "pad_token": "<pad>",
5
- "unk_token": "<unk>"
6
  }
 
1
  {
2
  "bos_token": "<s>",
3
  "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
  }
tokenizer_config.json CHANGED
@@ -1,36 +1,36 @@
1
  {
2
  "added_tokens_decoder": {
3
- "0": {
4
- "content": "<s>",
5
  "lstrip": true,
6
  "normalized": false,
7
  "rstrip": true,
8
  "single_word": false,
9
  "special": false
10
  },
11
- "1": {
12
- "content": "<pad>",
13
  "lstrip": true,
14
  "normalized": false,
15
  "rstrip": true,
16
  "single_word": false,
17
  "special": false
18
  },
19
- "2": {
20
- "content": "</s>",
21
- "lstrip": true,
22
  "normalized": false,
23
- "rstrip": true,
24
  "single_word": false,
25
- "special": false
26
  },
27
- "3": {
28
- "content": "<unk>",
29
- "lstrip": true,
30
  "normalized": false,
31
- "rstrip": true,
32
  "single_word": false,
33
- "special": false
34
  }
35
  },
36
  "additional_special_tokens": [],
@@ -39,11 +39,11 @@
39
  "do_lower_case": false,
40
  "eos_token": "</s>",
41
  "model_max_length": 1000000000000000019884624838656,
42
- "pad_token": "<pad>",
43
  "replace_word_delimiter_char": " ",
44
  "target_lang": null,
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
  "tokenizer_file": null,
47
- "unk_token": "<unk>",
48
  "word_delimiter_token": "|"
49
  }
 
1
  {
2
  "added_tokens_decoder": {
3
+ "88": {
4
+ "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
7
  "rstrip": true,
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "89": {
12
+ "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
15
  "rstrip": true,
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "90": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
  "normalized": false,
23
+ "rstrip": false,
24
  "single_word": false,
25
+ "special": true
26
  },
27
+ "91": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
  "normalized": false,
31
+ "rstrip": false,
32
  "single_word": false,
33
+ "special": true
34
  }
35
  },
36
  "additional_special_tokens": [],
 
39
  "do_lower_case": false,
40
  "eos_token": "</s>",
41
  "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "[PAD]",
43
  "replace_word_delimiter_char": " ",
44
  "target_lang": null,
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
  "tokenizer_file": null,
47
+ "unk_token": "[UNK]",
48
  "word_delimiter_token": "|"
49
  }
vocab.json CHANGED
@@ -1,69 +1,92 @@
1
  {
2
- "</s>": 2,
3
- "<pad>": 1,
4
- "<s>": 0,
5
- "<unk>": 3,
6
- "|": 4,
7
- "ँ": 5,
8
- "ं": 6,
9
- "ः": 7,
10
- "अ": 8,
11
- "आ": 9,
12
- "इ": 10,
13
- "ई": 11,
14
- "उ": 12,
15
- "ऊ": 13,
16
- "ऋ": 14,
17
- "ए": 15,
18
- "ऐ": 16,
19
- "ऑ": 17,
20
- "ओ": 18,
21
- "औ": 19,
22
- "क": 20,
23
- "ख": 21,
24
- "ग": 22,
25
- "घ": 23,
26
- "ङ": 24,
27
- "च": 25,
28
- "छ": 26,
29
- "ज": 27,
30
- "झ": 28,
31
- "ञ": 29,
32
- "ट": 30,
33
- "ठ": 31,
34
- "ड": 32,
35
- "ढ": 33,
36
- "ण": 34,
37
- "त": 35,
38
- "थ": 36,
39
- "द": 37,
40
- "ध": 38,
41
- "न": 39,
42
- "प": 40,
43
- "फ": 41,
44
- "ब": 42,
45
- "भ": 43,
46
- "म": 44,
47
- "य": 45,
48
- "र": 46,
49
- "ल": 47,
50
- "व": 48,
51
- "श": 49,
52
- "ष": 50,
53
- "स": 51,
54
- "ह": 52,
55
- "़": 53,
56
- "ा": 54,
57
- "ि": 55,
58
- "ी": 56,
59
- "ु": 57,
60
- "ू": 58,
61
- "ृ": 59,
62
- "ॅ": 60,
63
- "े": 61,
64
- "ै": 62,
65
- "ॉ": 63,
66
- "ो": 64,
67
- "ौ": 65,
68
- "्": 66
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
 
1
  {
2
+ " ": 0,
3
+ "/": 1,
4
+ "0": 2,
5
+ "1": 3,
6
+ "2": 4,
7
+ "3": 5,
8
+ "4": 6,
9
+ "5": 7,
10
+ "6": 8,
11
+ "7": 9,
12
+ "8": 10,
13
+ "9": 11,
14
+ "[PAD]": 89,
15
+ "[UNK]": 88,
16
+ "a": 12,
17
+ "c": 13,
18
+ "d": 14,
19
+ "e": 15,
20
+ "g": 16,
21
+ "h": 17,
22
+ "i": 18,
23
+ "l": 19,
24
+ "m": 20,
25
+ "n": 21,
26
+ "o": 22,
27
+ "p": 23,
28
+ "s": 24,
29
+ "t": 25,
30
+ "z": 26,
31
+ "ँ": 27,
32
+ "ं": 28,
33
+ "ः": 29,
34
+ "अ": 30,
35
+ "आ": 31,
36
+ "इ": 32,
37
+ "ई": 33,
38
+ "उ": 34,
39
+ "ऊ": 35,
40
+ "ए": 36,
41
+ "ऐ": 37,
42
+ "ऑ": 38,
43
+ "ओ": 39,
44
+ "औ": 40,
45
+ "क": 41,
46
+ "ख": 42,
47
+ "ग": 43,
48
+ "घ": 44,
49
+ "च": 45,
50
+ "छ": 46,
51
+ "ज": 47,
52
+ "झ": 48,
53
+ "ञ": 49,
54
+ "ट": 50,
55
+ "ठ": 51,
56
+ "ड": 52,
57
+ "ढ": 53,
58
+ "ण": 54,
59
+ "त": 55,
60
+ "थ": 56,
61
+ "द": 57,
62
+ "ध": 58,
63
+ "न": 59,
64
+ "प": 60,
65
+ "फ": 61,
66
+ "ब": 62,
67
+ "भ": 63,
68
+ "म": 64,
69
+ "य": 65,
70
+ "र": 66,
71
+ "ल": 67,
72
+ "व": 68,
73
+ "श": 69,
74
+ "ष": 70,
75
+ "स": 71,
76
+ "ह": 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
+ "्": 85,
90
+ "।": 86,
91
+ "‍": 87
92
  }