kiranpantha commited on
Commit
981653a
1 Parent(s): 1684b67

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -5
  3. vocab.json +53 -60
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 71,
3
- "<s>": 70
4
  }
 
1
  {
2
+ "</s>": 64,
3
+ "<s>": 63
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "68": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "69": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "70": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "71": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
@@ -39,7 +39,6 @@
39
  "eos_token": "</s>",
40
  "model_max_length": 1000000000000000019884624838656,
41
  "pad_token": "[PAD]",
42
- "processor_class": "Wav2Vec2BertProcessor",
43
  "replace_word_delimiter_char": " ",
44
  "target_lang": null,
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
1
  {
2
  "added_tokens_decoder": {
3
+ "61": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "62": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "63": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "64": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
39
  "eos_token": "</s>",
40
  "model_max_length": 1000000000000000019884624838656,
41
  "pad_token": "[PAD]",
 
42
  "replace_word_delimiter_char": " ",
43
  "target_lang": null,
44
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
vocab.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "[PAD]": 69,
3
- "[UNK]": 68,
4
  "|": 0,
5
  "ँ": 1,
6
  "ं": 2,
@@ -11,62 +11,55 @@
11
  "ई": 7,
12
  "उ": 8,
13
  "ऊ": 9,
14
- "": 10,
15
- "": 11,
16
- "": 12,
17
- "": 13,
18
- "": 14,
19
- "": 15,
20
- "": 16,
21
- "": 17,
22
- "": 18,
23
- "": 19,
24
- "": 20,
25
- "": 21,
26
- "": 22,
27
- "": 23,
28
- "": 24,
29
- "": 25,
30
- "": 26,
31
- "": 27,
32
- "": 28,
33
- "": 29,
34
- "": 30,
35
- "": 31,
36
- "": 32,
37
- "": 33,
38
- "": 34,
39
- "": 35,
40
- "": 36,
41
- "": 37,
42
- "": 38,
43
- "": 39,
44
- "": 40,
45
- "": 41,
46
- "": 42,
47
- "": 43,
48
- "": 44,
49
- "": 45,
50
- "": 46,
51
- "": 47,
52
- "": 48,
53
- "": 49,
54
- "ि": 50,
55
- "": 51,
56
- "": 52,
57
- "": 53,
58
- "": 54,
59
- "": 55,
60
- "": 56,
61
- "": 57,
62
- "": 58,
63
- "": 59,
64
- "": 60,
65
- "ॐ": 61,
66
- "ॠ": 62,
67
- "।": 63,
68
- "॰": 64,
69
- "‌": 65,
70
- "‍": 66,
71
- "‎": 67
72
  }
 
1
  {
2
+ "[PAD]": 62,
3
+ "[UNK]": 61,
4
  "|": 0,
5
  "ँ": 1,
6
  "ं": 2,
 
11
  "ई": 7,
12
  "उ": 8,
13
  "ऊ": 9,
14
+ "": 10,
15
+ "": 11,
16
+ "": 12,
17
+ "": 13,
18
+ "": 14,
19
+ "": 15,
20
+ "": 16,
21
+ "": 17,
22
+ "": 18,
23
+ "": 19,
24
+ "": 20,
25
+ "": 21,
26
+ "": 22,
27
+ "": 23,
28
+ "": 24,
29
+ "": 25,
30
+ "": 26,
31
+ "": 27,
32
+ "": 28,
33
+ "": 29,
34
+ "": 30,
35
+ "": 31,
36
+ "": 32,
37
+ "": 33,
38
+ "": 34,
39
+ "": 35,
40
+ "": 36,
41
+ "": 37,
42
+ "": 38,
43
+ "": 39,
44
+ "": 40,
45
+ "": 41,
46
+ "": 42,
47
+ "": 43,
48
+ "": 44,
49
+ "": 45,
50
+ "": 46,
51
+ "": 47,
52
+ "ि": 48,
53
+ "": 49,
54
+ "": 50,
55
+ "": 51,
56
+ "": 52,
57
+ "": 53,
58
+ "": 54,
59
+ "": 55,
60
+ "": 56,
61
+ "": 57,
62
+ "": 58,
63
+ "": 59,
64
+ "": 60
 
 
 
 
 
 
 
65
  }