newknp commited on
Commit
26af622
·
1 Parent(s): 4edcc55

End of training

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 68,
3
+ "<s>": 67
4
+ }
preprocessor_config.json CHANGED
@@ -4,6 +4,7 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
 
7
  "return_attention_mask": true,
8
  "sampling_rate": 16000
9
  }
 
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
  "return_attention_mask": true,
9
  "sampling_rate": 16000
10
  }
special_tokens_map.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
19
+ "eos_token": "</s>",
20
+ "pad_token": "[PAD]",
21
+ "unk_token": "[UNK]"
22
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": ".",
7
+ "pad_token": "[PAD]",
8
+ "processor_class": "Wav2Vec2Processor",
9
+ "replace_word_delimiter_char": " ",
10
+ "special_tokens_map_file": null,
11
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
12
+ "unk_token": "[UNK]",
13
+ "word_delimiter_token": "|"
14
+ }
vocab.json CHANGED
@@ -1 +1,69 @@
1
- {"\u0e01": 1, "\u0e02": 2, "\u0e04": 3, "\u0e06": 4, "\u0e07": 5, "\u0e08": 6, "\u0e09": 7, "\u0e0a": 8, "\u0e0b": 9, "\u0e0c": 10, "\u0e0d": 11, "\u0e0e": 12, "\u0e0f": 13, "\u0e10": 14, "\u0e11": 15, "\u0e12": 16, "\u0e13": 17, "\u0e14": 18, "\u0e15": 19, "\u0e16": 20, "\u0e17": 21, "\u0e18": 22, "\u0e19": 23, "\u0e1a": 24, "\u0e1b": 25, "\u0e1c": 26, "\u0e1d": 27, "\u0e1e": 28, "\u0e1f": 29, "\u0e20": 30, "\u0e21": 31, "\u0e22": 32, "\u0e23": 33, "\u0e24": 34, "\u0e25": 35, "\u0e27": 36, "\u0e28": 37, "\u0e29": 38, "\u0e2a": 39, "\u0e2b": 40, "\u0e2c": 41, "\u0e2d": 42, "\u0e2e": 43, "\u0e30": 44, "\u0e31": 45, "\u0e32": 46, "\u0e33": 47, "\u0e34": 48, "\u0e35": 49, "\u0e36": 50, "\u0e37": 51, "\u0e38": 52, "\u0e39": 53, "\u0e40": 54, "\u0e41": 55, "\u0e42": 56, "\u0e43": 57, "\u0e44": 58, "\u0e47": 59, "\u0e48": 60, "\u0e49": 61, "\u0e4a": 62, "\u0e4b": 63, "\u0e4c": 64, "|": 0, "[UNK]": 65, "[PAD]": 66}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 66,
3
+ "[UNK]": 65,
4
+ "|": 0,
5
+ "ก": 1,
6
+ "ข": 2,
7
+ "ค": 3,
8
+ "ฆ": 4,
9
+ "ง": 5,
10
+ "จ": 6,
11
+ "ฉ": 7,
12
+ "ช": 8,
13
+ "ซ": 9,
14
+ "ฌ": 10,
15
+ "ญ": 11,
16
+ "ฎ": 12,
17
+ "ฏ": 13,
18
+ "ฐ": 14,
19
+ "ฑ": 15,
20
+ "ฒ": 16,
21
+ "ณ": 17,
22
+ "ด": 18,
23
+ "ต": 19,
24
+ "ถ": 20,
25
+ "ท": 21,
26
+ "ธ": 22,
27
+ "น": 23,
28
+ "บ": 24,
29
+ "ป": 25,
30
+ "ผ": 26,
31
+ "ฝ": 27,
32
+ "พ": 28,
33
+ "ฟ": 29,
34
+ "ภ": 30,
35
+ "ม": 31,
36
+ "ย": 32,
37
+ "ร": 33,
38
+ "ฤ": 34,
39
+ "ล": 35,
40
+ "ว": 36,
41
+ "ศ": 37,
42
+ "ษ": 38,
43
+ "ส": 39,
44
+ "ห": 40,
45
+ "ฬ": 41,
46
+ "อ": 42,
47
+ "ฮ": 43,
48
+ "ะ": 44,
49
+ "ั": 45,
50
+ "า": 46,
51
+ "ำ": 47,
52
+ "ิ": 48,
53
+ "ี": 49,
54
+ "ึ": 50,
55
+ "ื": 51,
56
+ "ุ": 52,
57
+ "ู": 53,
58
+ "เ": 54,
59
+ "แ": 55,
60
+ "โ": 56,
61
+ "ใ": 57,
62
+ "ไ": 58,
63
+ "็": 59,
64
+ "่": 60,
65
+ "้": 61,
66
+ "๊": 62,
67
+ "๋": 63,
68
+ "์": 64
69
+ }