Hugging Face's logo

liampower
/
wav2vec2-dali-ft

Transformers
Model card Files
xet
 Community
liampower commited on
Commit
0f93b70
·
verified ·
1 Parent(s): 9b9641c

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +2 -2
  2. tokenizer_config.json +10 -10
  3. vocab.json +30 -28
special_tokens_map.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "bos_token": "<s>",
3
  "eos_token": "</s>",
4
- "pad_token": "[PAD]",
5
- "unk_token": "[UNK]"
6
  }
 
1
  {
2
  "bos_token": "<s>",
3
  "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
  }
tokenizer_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "added_tokens_decoder": {
3
  "28": {
4
- "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
7
  "rstrip": true,
@@ -9,7 +9,7 @@
9
  "special": false
10
  },
11
  "29": {
12
- "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
15
  "rstrip": true,
@@ -18,19 +18,19 @@
18
  },
19
  "30": {
20
  "content": "<s>",
21
- "lstrip": false,
22
  "normalized": false,
23
- "rstrip": false,
24
  "single_word": false,
25
- "special": true
26
  },
27
  "31": {
28
  "content": "</s>",
29
- "lstrip": false,
30
  "normalized": false,
31
- "rstrip": false,
32
  "single_word": false,
33
- "special": true
34
  }
35
  },
36
  "bos_token": "<s>",
@@ -39,10 +39,10 @@
39
  "eos_token": "</s>",
40
  "extra_special_tokens": {},
41
  "model_max_length": 1000000000000000019884624838656,
42
- "pad_token": "[PAD]",
43
  "replace_word_delimiter_char": " ",
44
  "target_lang": null,
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
- "unk_token": "[UNK]",
47
  "word_delimiter_token": "|"
48
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "28": {
4
+ "content": "<unk>",
5
  "lstrip": true,
6
  "normalized": false,
7
  "rstrip": true,
 
9
  "special": false
10
  },
11
  "29": {
12
+ "content": "<pad>",
13
  "lstrip": true,
14
  "normalized": false,
15
  "rstrip": true,
 
18
  },
19
  "30": {
20
  "content": "<s>",
21
+ "lstrip": true,
22
  "normalized": false,
23
+ "rstrip": true,
24
  "single_word": false,
25
+ "special": false
26
  },
27
  "31": {
28
  "content": "</s>",
29
+ "lstrip": true,
30
  "normalized": false,
31
+ "rstrip": true,
32
  "single_word": false,
33
+ "special": false
34
  }
35
  },
36
  "bos_token": "<s>",
 
39
  "eos_token": "</s>",
40
  "extra_special_tokens": {},
41
  "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<pad>",
43
  "replace_word_delimiter_char": " ",
44
  "target_lang": null,
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "unk_token": "<unk>",
47
  "word_delimiter_token": "|"
48
  }
vocab.json CHANGED
@@ -1,32 +1,34 @@
1
  {
2
  "'": 1,
3
- "[PAD]": 29,
4
- "[UNK]": 28,
5
- "a": 2,
6
- "b": 3,
7
- "c": 4,
8
- "d": 5,
9
- "e": 6,
10
- "f": 7,
11
- "g": 8,
12
- "h": 9,
13
- "i": 10,
14
- "j": 11,
15
- "k": 12,
16
- "l": 13,
17
- "m": 14,
18
- "n": 15,
19
- "o": 16,
20
- "p": 17,
21
- "q": 18,
22
- "r": 19,
23
- "s": 20,
24
- "t": 21,
25
- "u": 22,
26
- "v": 23,
27
- "w": 24,
28
- "x": 25,
29
- "y": 26,
30
- "z": 27,
 
 
31
  "|": 0
32
  }
 
1
  {
2
  "'": 1,
3
+ "</s>": 31,
4
+ "<pad>": 29,
5
+ "<s>": 30,
6
+ "<unk>": 28,
7
+ "A": 2,
8
+ "B": 3,
9
+ "C": 4,
10
+ "D": 5,
11
+ "E": 6,
12
+ "F": 7,
13
+ "G": 8,
14
+ "H": 9,
15
+ "I": 10,
16
+ "J": 11,
17
+ "K": 12,
18
+ "L": 13,
19
+ "M": 14,
20
+ "N": 15,
21
+ "O": 16,
22
+ "P": 17,
23
+ "Q": 18,
24
+ "R": 19,
25
+ "S": 20,
26
+ "T": 21,
27
+ "U": 22,
28
+ "V": 23,
29
+ "W": 24,
30
+ "X": 25,
31
+ "Y": 26,
32
+ "Z": 27,
33
  "|": 0
34
  }