Hugging Face's logo

Rima
/
wav2vec2-L

Transformers
Model card Files
xet
 Community
Rima commited on
Commit
48a62a5
·
verified ·
1 Parent(s): e943aae

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +2 -2
  2. tokenizer_config.json +19 -17
  3. vocab.json +56 -50
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
@@ -1,48 +1,50 @@
1
  {
2
  "added_tokens_decoder": {
3
- "48": {
4
- "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
7
  "rstrip": true,
8
  "single_word": false,
9
  "special": false
10
  },
11
- "49": {
12
- "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
15
  "rstrip": true,
16
  "single_word": false,
17
  "special": false
18
  },
19
- "50": {
20
- "content": "<s>",
21
- "lstrip": false,
22
  "normalized": false,
23
- "rstrip": false,
24
  "single_word": false,
25
- "special": true
26
  },
27
- "51": {
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>",
37
  "clean_up_tokenization_spaces": false,
38
  "do_lower_case": false,
 
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
+ "0": {
4
+ "content": "<pad>",
5
  "lstrip": true,
6
  "normalized": false,
7
  "rstrip": true,
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "1": {
12
+ "content": "<s>",
13
  "lstrip": true,
14
  "normalized": false,
15
  "rstrip": true,
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": true,
22
  "normalized": false,
23
+ "rstrip": true,
24
  "single_word": false,
25
+ "special": false
26
  },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": true,
30
  "normalized": false,
31
+ "rstrip": true,
32
  "single_word": false,
33
+ "special": false
34
  }
35
  },
36
  "bos_token": "<s>",
37
  "clean_up_tokenization_spaces": false,
38
  "do_lower_case": false,
39
+ "do_normalize": true,
40
  "eos_token": "</s>",
41
  "extra_special_tokens": {},
42
  "model_max_length": 1000000000000000019884624838656,
43
+ "pad_token": "<pad>",
44
  "replace_word_delimiter_char": " ",
45
+ "return_attention_mask": false,
46
  "target_lang": null,
47
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
48
+ "unk_token": "<unk>",
49
+ "word_delimiter_token": "/"
50
  }
vocab.json CHANGED
@@ -1,52 +1,58 @@
1
  {
2
- "[PAD]": 49,
3
- "[UNK]": 48,
4
- "|": 9,
5
- "ء": 5,
6
- "آ": 20,
7
- "أ": 27,
8
- "ؤ": 11,
9
- "إ": 2,
10
- "ئ": 42,
11
- "ا": 3,
12
- "ب": 45,
13
- "ة": 31,
14
- "ت": 17,
15
- "ث": 24,
16
- "ج": 13,
17
- "ح": 41,
18
- "خ": 38,
19
- "د": 33,
20
- "ذ": 12,
21
- "ر": 29,
22
- "ز": 4,
23
- "س": 44,
24
- "ش": 16,
25
- "ص": 8,
26
- "ض": 21,
27
- "ط": 40,
28
- "ظ": 22,
29
- "ع": 10,
30
- "غ": 19,
31
- "ف": 0,
32
- "ق": 37,
33
- "ك": 15,
34
- "ل": 23,
35
- "م": 7,
36
- "ن": 39,
37
- "ه": 18,
38
- "و": 36,
39
- "ى": 32,
40
- "ي": 26,
41
- "ً": 35,
42
- "ٌ": 25,
43
- "ٍ": 46,
44
- "َ": 47,
45
- "ُ": 34,
46
- "ِ": 28,
47
- "ّ": 43,
48
- "ْ": 30,
49
- "ٰ": 14,
50
- "ک": 6,
51
- "ی": 1
 
 
 
 
 
 
52
  }
 
1
  {
2
+ "$": 24,
3
+ "&": 8,
4
+ "'": 5,
5
+ "*": 20,
6
+ "/": 4,
7
+ "<": 9,
8
+ "</s>": 2,
9
+ "<pad>": 0,
10
+ "<s>": 1,
11
+ "<unk>": 3,
12
+ ">": 7,
13
+ "A": 11,
14
+ "D": 26,
15
+ "E": 29,
16
+ "F": 42,
17
+ "G": 55,
18
+ "H": 17,
19
+ "J": 53,
20
+ "K": 44,
21
+ "N": 43,
22
+ "P": 52,
23
+ "S": 25,
24
+ "T": 27,
25
+ "V": 54,
26
+ "Y": 40,
27
+ "Z": 28,
28
+ "_": 31,
29
+ "`": 50,
30
+ "a": 45,
31
+ "b": 12,
32
+ "d": 19,
33
+ "f": 32,
34
+ "g": 30,
35
+ "h": 38,
36
+ "i": 47,
37
+ "j": 16,
38
+ "k": 34,
39
+ "l": 35,
40
+ "m": 36,
41
+ "n": 37,
42
+ "o": 49,
43
+ "p": 13,
44
+ "q": 33,
45
+ "r": 21,
46
+ "s": 23,
47
+ "t": 14,
48
+ "u": 46,
49
+ "v": 15,
50
+ "w": 39,
51
+ "x": 18,
52
+ "y": 41,
53
+ "z": 22,
54
+ "{": 51,
55
+ "|": 6,
56
+ "}": 10,
57
+ "~": 48
58
  }