Hugging Face's logo

akhikhan123
/
xlsr-wav2vec2-model

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
akhikhan123 commited on
Commit
4b2807d
•
1 Parent(s): 542206e

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +53 -60
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 87,
3
- "<s>": 86
4
  }
 
1
  {
2
+ "</s>": 80,
3
+ "<s>": 79
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "84": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "85": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "86": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "87": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "77": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "78": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "79": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "80": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  " ": 0,
3
- "[PAD]": 85,
4
- "[UNK]": 84,
5
  "a": 1,
6
  "b": 2,
7
  "c": 3,
@@ -27,62 +27,55 @@
27
  "w": 23,
28
  "x": 24,
29
  "y": 25,
30
- "z": 26,
31
- "|": 83,
32
- "ঁ": 27,
33
- "ং": 28,
34
- "অ": 29,
35
- "আ": 30,
36
- "ই": 31,
37
- "ঈ": 32,
38
- "উ": 33,
39
- "এ": 34,
40
- "ও": 35,
41
- "ঔ": 36,
42
- "ক": 37,
43
- "খ": 38,
44
- "গ": 39,
45
- "ঘ": 40,
46
- "ঙ": 41,
47
- "চ": 42,
48
- "ছ": 43,
49
- "জ": 44,
50
- "ঝ": 45,
51
- "ঞ": 46,
52
- "ট": 47,
53
- "ঠ": 48,
54
- "ড": 49,
55
- "ণ": 50,
56
- "ত": 51,
57
- "থ": 52,
58
- "দ": 53,
59
- "ধ": 54,
60
- "ন": 55,
61
- "প": 56,
62
- "ফ": 57,
63
- "ব": 58,
64
- "ভ": 59,
65
- "ম": 60,
66
- "য": 61,
67
- "র": 62,
68
- "ল": 63,
69
- "শ": 64,
70
- "ষ": 65,
71
- "স": 66,
72
- "হ": 67,
73
- "়": 68,
74
- "া": 69,
75
- "ি": 70,
76
- "ী": 71,
77
- "ু": 72,
78
- "ূ": 73,
79
- "ৃ": 74,
80
- "ে": 75,
81
- "ৈ": 76,
82
- "ো": 77,
83
- "ৌ": 78,
84
- "্": 79,
85
- "ৎ": 80,
86
- "ড়": 81,
87
- "য়": 82
88
  }
 
1
  {
2
  " ": 0,
3
+ "[PAD]": 78,
4
+ "[UNK]": 77,
5
  "a": 1,
6
  "b": 2,
7
  "c": 3,
 
27
  "w": 23,
28
  "x": 24,
29
  "y": 25,
30
+ "|": 76,
31
+ "ঁ": 26,
32
+ "ং": 27,
33
+ "অ": 28,
34
+ "আ": 29,
35
+ "ই": 30,
36
+ "ঈ": 31,
37
+ "উ": 32,
38
+ "এ": 33,
39
+ "ও": 34,
40
+ "ক": 35,
41
+ "খ": 36,
42
+ "গ": 37,
43
+ "ঘ": 38,
44
+ "ঙ": 39,
45
+ "চ": 40,
46
+ "ছ": 41,
47
+ "জ": 42,
48
+ "ঞ": 43,
49
+ "ট": 44,
50
+ "ঠ": 45,
51
+ "ড": 46,
52
+ "ণ": 47,
53
+ "ত": 48,
54
+ "থ": 49,
55
+ "দ": 50,
56
+ "ধ": 51,
57
+ "ন": 52,
58
+ "প": 53,
59
+ "ফ": 54,
60
+ "ব": 55,
61
+ "ভ": 56,
62
+ "ম": 57,
63
+ "য": 58,
64
+ "র": 59,
65
+ "ল": 60,
66
+ "শ": 61,
67
+ "ষ": 62,
68
+ "স": 63,
69
+ "হ": 64,
70
+ "়": 65,
71
+ "া": 66,
72
+ "ি": 67,
73
+ "ী": 68,
74
+ "ু": 69,
75
+ "ৃ": 70,
76
+ "ে": 71,
77
+ "ো": 72,
78
+ "্": 73,
79
+ "ড়": 74,
80
+ "য়": 75
 
 
 
 
 
 
 
81
  }