Hugging Face's logo

shrria
/
bts-asr-processor

Automatic Speech Recognition
Transformers
PyTorch
Thai
wav2vec2
Inference Endpoints
Model card Files Community
shrria commited on
Commit
b348739
•
1 Parent(s): ba8cf0a

Commit from local

Browse files
Files changed (9) hide show
  1. added_tokens.json +4 -0
  2. alphabet.json +1 -0
  3. language_model/attrs.json +1 -0
  4. language_model/bts.mclass.lm +0 -0
  5. language_model/unigrams.txt +0 -0
  6. preprocessor_config.json +10 -0
  7. special_tokens_map.json +50 -0
  8. tokenizer_config.json +14 -0
  9. vocab.json +72 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 71,
3
+ "<s>": 70
4
+ }
alphabet.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"labels": ["\u0e37", "\u0e0a", "\u0e2e", "\u0e08", "\u0e31", "\u0e2b", "\u0e09", "\u0e04", "\u0e02", "\u0e06", "\u0e49", "\u0e27", "\u0e22", "\u0e2f", "\u0e43", "\u0e20", "\u0e23", "\u0e48", "\u0e14", "\u0e33", "\u0e42", "\u0e4b", "\u0e24", "\u0e0e", "\u0e45", "\u0e40", "\u0e16", "\u0e1c", "\u0e34", "\u0e13", "\u0e1a", "\u0e1d", "\u0e0c", "\u0e17", "\u0e15", "\u0e10", "\u0e11", "\u0e12", "\u0e28", "\u0e4a", "\u0e2c", "\u0e30", "\u0e41", "\u0e01", "\u0e47", "\u0e39", " ", "\u0e32", "\u0e0d", "\u0e18", "\u0e36", "\u0e07", "\u0e29", "\u0e35", "\u0e19", "\u0e25", "\u0e0b", "\u0e0f", "\u0e2a", "\u0e44", "\u0e38", "\u0e2d", "\u0e1e", "\u0e1f", "\u0e03", "\u0e1b", "\u0e21", "\u0e4c", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
language_model/attrs.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}
language_model/bts.mclass.lm ADDED
The diff for this file is too large to render. See raw diff
 
language_model/unigrams.txt ADDED
File without changes
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2ProcessorWithLM",
8
+ "return_attention_mask": false,
9
+ "sampling_rate": 16000
10
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<s>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<s>",
33
+ "lstrip": false,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "</s>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ }
45
+ ],
46
+ "bos_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "pad_token": "[PAD]",
49
+ "unk_token": "[UNK]"
50
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "processor_class": "Wav2Vec2ProcessorWithLM",
9
+ "replace_word_delimiter_char": " ",
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "trust_remote_code": false,
12
+ "unk_token": "[UNK]",
13
+ "word_delimiter_token": "|"
14
+ }
vocab.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 69,
3
+ "[UNK]": 68,
4
+ "|": 46,
5
+ "ก": 43,
6
+ "ข": 8,
7
+ "ฃ": 64,
8
+ "ค": 7,
9
+ "ฆ": 9,
10
+ "ง": 51,
11
+ "จ": 3,
12
+ "ฉ": 6,
13
+ "ช": 1,
14
+ "ซ": 56,
15
+ "ฌ": 32,
16
+ "ญ": 48,
17
+ "ฎ": 23,
18
+ "ฏ": 57,
19
+ "ฐ": 35,
20
+ "ฑ": 36,
21
+ "ฒ": 37,
22
+ "ณ": 29,
23
+ "ด": 18,
24
+ "ต": 34,
25
+ "ถ": 26,
26
+ "ท": 33,
27
+ "ธ": 49,
28
+ "น": 54,
29
+ "บ": 30,
30
+ "ป": 65,
31
+ "ผ": 27,
32
+ "ฝ": 31,
33
+ "พ": 62,
34
+ "ฟ": 63,
35
+ "ภ": 15,
36
+ "ม": 66,
37
+ "ย": 12,
38
+ "ร": 16,
39
+ "ฤ": 22,
40
+ "ล": 55,
41
+ "ว": 11,
42
+ "ศ": 38,
43
+ "ษ": 52,
44
+ "ส": 58,
45
+ "ห": 5,
46
+ "ฬ": 40,
47
+ "อ": 61,
48
+ "ฮ": 2,
49
+ "ฯ": 13,
50
+ "ะ": 41,
51
+ "ั": 4,
52
+ "า": 47,
53
+ "ำ": 19,
54
+ "ิ": 28,
55
+ "ี": 53,
56
+ "ึ": 50,
57
+ "ื": 0,
58
+ "ุ": 60,
59
+ "ู": 45,
60
+ "เ": 25,
61
+ "แ": 42,
62
+ "โ": 20,
63
+ "ใ": 14,
64
+ "ไ": 59,
65
+ "ๅ": 24,
66
+ "็": 44,
67
+ "่": 17,
68
+ "้": 10,
69
+ "๊": 39,
70
+ "๋": 21,
71
+ "์": 67
72
+ }