Hugging Face's logo

Thunpitcha
/
wav2vec2-base-thai-5-google-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Thunpitcha commited on
Commit
da9264e
•
1 Parent(s): 77e3ae9

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +6 -0
  3. tokenizer_config.json +47 -0
  4. vocab.json +90 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 89,
3
+ "<s>": 88
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "86": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "87": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "88": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "89": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": 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",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 57,
3
+ "[PAD]": 87,
4
+ "[UNK]": 86,
5
+ "_": 49,
6
+ "a": 76,
7
+ "c": 34,
8
+ "e": 60,
9
+ "h": 31,
10
+ "i": 10,
11
+ "j": 22,
12
+ "k": 32,
13
+ "l": 48,
14
+ "m": 85,
15
+ "n": 59,
16
+ "o": 16,
17
+ "r": 55,
18
+ "s": 79,
19
+ "t": 27,
20
+ "y": 13,
21
+ "|": 3,
22
+ "~": 84,
23
+ "ก": 6,
24
+ "ข": 5,
25
+ "ค": 41,
26
+ "ฆ": 66,
27
+ "ง": 78,
28
+ "จ": 33,
29
+ "ฉ": 26,
30
+ "ช": 64,
31
+ "ซ": 46,
32
+ "ฌ": 29,
33
+ "ญ": 56,
34
+ "ฎ": 39,
35
+ "ฏ": 53,
36
+ "ฐ": 35,
37
+ "ฑ": 69,
38
+ "ฒ": 74,
39
+ "ณ": 37,
40
+ "ด": 43,
41
+ "ต": 4,
42
+ "ถ": 25,
43
+ "ท": 21,
44
+ "ธ": 71,
45
+ "น": 61,
46
+ "บ": 14,
47
+ "ป": 72,
48
+ "ผ": 68,
49
+ "ฝ": 9,
50
+ "พ": 62,
51
+ "ฟ": 80,
52
+ "ภ": 28,
53
+ "ม": 12,
54
+ "ย": 75,
55
+ "ร": 54,
56
+ "ฤ": 52,
57
+ "ล": 0,
58
+ "ว": 58,
59
+ "ศ": 7,
60
+ "ษ": 47,
61
+ "ส": 17,
62
+ "ห": 20,
63
+ "ฬ": 19,
64
+ "อ": 50,
65
+ "ฮ": 51,
66
+ "ะ": 42,
67
+ "ั": 38,
68
+ "า": 11,
69
+ "ำ": 65,
70
+ "ิ": 18,
71
+ "ี": 40,
72
+ "ึ": 67,
73
+ "ื": 2,
74
+ "ุ": 15,
75
+ "ู": 73,
76
+ "เ": 45,
77
+ "แ": 8,
78
+ "โ": 77,
79
+ "ใ": 83,
80
+ "ไ": 70,
81
+ "ๅ": 63,
82
+ "ๆ": 30,
83
+ "็": 82,
84
+ "่": 36,
85
+ "้": 23,
86
+ "๊": 24,
87
+ "๋": 44,
88
+ "์": 81,
89
+ "’": 1
90
+ }