Hugging Face's logo

Thunpitcha
/
wav2vec2-base-thai-demo-google-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Thunpitcha commited on
Commit
a2a1b97
•
1 Parent(s): bbc9198

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +68 -70
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 71,
3
- "<s>": 70
4
  }
 
1
  {
2
+ "</s>": 69,
3
+ "<s>": 68
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": true,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "71": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": true,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "66": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "67": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "68": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": true,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "69": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": true,
vocab.json CHANGED
@@ -1,72 +1,70 @@
1
  {
2
- "'": 6,
3
- "[PAD]": 69,
4
- "[UNK]": 68,
5
- "|": 34,
6
- "ก": 37,
7
- "ข": 55,
8
- "ค": 26,
9
- "ฆ": 21,
10
- "ง": 2,
11
- "จ": 18,
12
- "ฉ": 7,
13
- "ช": 20,
14
- "ซ": 57,
15
- "ญ": 43,
16
- "ฎ": 39,
17
- "ฏ": 11,
18
- "ฐ": 31,
19
- "ฑ": 66,
20
- "ฒ": 50,
21
- "ณ": 36,
22
- "ด": 51,
23
- "ต": 15,
24
- "ถ": 5,
25
- "ท": 22,
26
- "ธ": 48,
27
- "น": 56,
28
- "บ": 4,
29
- "ป": 25,
30
- "ผ": 14,
31
- "ฝ": 1,
32
- "พ": 35,
33
- "ฟ": 24,
34
- "ภ": 27,
35
- "ม": 30,
36
- "ย": 0,
37
- "ร": 62,
38
- "ฤ": 9,
39
- "ล": 19,
40
- "ว": 45,
41
- "ศ": 3,
42
- "ษ": 44,
43
- "ส": 63,
44
- "ห": 49,
45
- "ฬ": 60,
46
- "อ": 29,
47
- "ฮ": 42,
48
- "ะ": 53,
49
- "ั": 8,
50
- "า": 64,
51
- "ำ": 40,
52
- "ิ": 13,
53
- "ี": 38,
54
- "ึ": 12,
55
- "ื": 54,
56
- "ุ": 61,
57
- "ู": 47,
58
- "เ": 17,
59
- "แ": 28,
60
- "โ": 52,
61
- "ใ": 67,
62
- "ไ": 46,
63
- "ๆ": 41,
64
- "็": 59,
65
- "่": 23,
66
- "้": 58,
67
- "๊": 16,
68
- "๋": 33,
69
- "์": 10,
70
- "“": 65,
71
- "”": 32
72
  }
 
1
  {
2
+ "'": 37,
3
+ "[PAD]": 67,
4
+ "[UNK]": 66,
5
+ "|": 20,
6
+ "ก": 7,
7
+ "ข": 24,
8
+ "ค": 45,
9
+ "ฆ": 4,
10
+ "ง": 9,
11
+ "จ": 60,
12
+ "ฉ": 17,
13
+ "ช": 15,
14
+ "ซ": 43,
15
+ "ญ": 64,
16
+ "ฎ": 40,
17
+ "ฏ": 42,
18
+ "ฐ": 26,
19
+ "ฑ": 14,
20
+ "ฒ": 38,
21
+ "ณ": 44,
22
+ "ด": 13,
23
+ "ต": 61,
24
+ "ถ": 47,
25
+ "ท": 65,
26
+ "ธ": 31,
27
+ "น": 53,
28
+ "บ": 55,
29
+ "ป": 16,
30
+ "ผ": 39,
31
+ "ฝ": 10,
32
+ "พ": 48,
33
+ "ฟ": 57,
34
+ "ภ": 29,
35
+ "ม": 34,
36
+ "ย": 28,
37
+ "ร": 41,
38
+ "ฤ": 5,
39
+ "ล": 22,
40
+ "ว": 33,
41
+ "ศ": 18,
42
+ "ษ": 52,
43
+ "ส": 30,
44
+ "ห": 46,
45
+ "ฬ": 8,
46
+ "อ": 3,
47
+ "ฮ": 35,
48
+ "ะ": 0,
49
+ "ั": 54,
50
+ "า": 1,
51
+ "ำ": 23,
52
+ "ิ": 25,
53
+ "ี": 51,
54
+ "ึ": 59,
55
+ "ื": 32,
56
+ "ุ": 2,
57
+ "ู": 49,
58
+ "เ": 62,
59
+ "แ": 56,
60
+ "โ": 11,
61
+ "ใ": 58,
62
+ "ไ": 27,
63
+ "ๆ": 21,
64
+ "็": 12,
65
+ "่": 63,
66
+ "้": 6,
67
+ "๊": 50,
68
+ "๋": 36,
69
+ "์": 19
 
 
70
  }