monideep2255 commited on
Commit
247f683
1 Parent(s): e6c3aca

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +17 -0
  3. vocab.json +48 -0
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 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "replace_word_delimiter_char": " ",
9
+ "reserved_token1": "?reserved2?",
10
+ "reserved_token2": "?reserved3?",
11
+ "silence_token": "<sil>",
12
+ "spoken_noise_token": "<spn>",
13
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
14
+ "unk_token": "<unk>",
15
+ "vocab_size": 46,
16
+ "word_delimiter_token": "|"
17
+ }
vocab.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<pad>": 16,
3
+ "<sil>": 32,
4
+ "<spn>": 12,
5
+ "<unk>": 24,
6
+ "?reserved2?": 7,
7
+ "?reserved3?": 29,
8
+ "AA": 27,
9
+ "AE": 11,
10
+ "AH": 28,
11
+ "AO": 17,
12
+ "AW": 13,
13
+ "AY": 20,
14
+ "B": 4,
15
+ "CH": 1,
16
+ "D": 6,
17
+ "DH": 19,
18
+ "DX": 31,
19
+ "EH": 10,
20
+ "ER": 30,
21
+ "EY": 15,
22
+ "F": 22,
23
+ "G": 3,
24
+ "HH": 5,
25
+ "IH": 39,
26
+ "IY": 21,
27
+ "JH": 43,
28
+ "K": 33,
29
+ "L": 23,
30
+ "M": 0,
31
+ "N": 25,
32
+ "NG": 40,
33
+ "OW": 2,
34
+ "OY": 42,
35
+ "P": 18,
36
+ "R": 14,
37
+ "S": 45,
38
+ "SH": 9,
39
+ "T": 35,
40
+ "TH": 36,
41
+ "UH": 37,
42
+ "UW": 41,
43
+ "V": 8,
44
+ "W": 34,
45
+ "Y": 26,
46
+ "Z": 44,
47
+ "ZH": 38
48
+ }