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
bbc9198
•
1 Parent(s): 173e953

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 +72 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 71,
3
+ "<s>": 70
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
+ "68": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "69": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "70": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "71": {
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 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }