Hugging Face's logo

web2savar
/
mactest2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
web2savar commited on
Commit
86b5790
·
verified ·
1 Parent(s): 8463de3

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -5
  3. vocab.json +37 -50
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 52,
3
- "<s>": 51
4
  }
 
1
  {
2
+ "</s>": 39,
3
+ "<s>": 38
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "49": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "50": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "51": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "52": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
@@ -39,7 +39,6 @@
39
  "eos_token": "</s>",
40
  "model_max_length": 1000000000000000019884624838656,
41
  "pad_token": "[PAD]",
42
- "processor_class": "Wav2Vec2BertProcessor",
43
  "replace_word_delimiter_char": " ",
44
  "target_lang": null,
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
1
  {
2
  "added_tokens_decoder": {
3
+ "36": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "37": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "38": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "39": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
39
  "eos_token": "</s>",
40
  "model_max_length": 1000000000000000019884624838656,
41
  "pad_token": "[PAD]",
 
42
  "replace_word_delimiter_char": " ",
43
  "target_lang": null,
44
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
vocab.json CHANGED
@@ -1,53 +1,40 @@
1
  {
2
- "!": 1,
3
- "\"": 2,
4
- "'": 3,
5
- "(": 4,
6
- ")": 5,
7
- ",": 6,
8
- "-": 7,
9
- ".": 8,
10
- ":": 9,
11
- ";": 10,
12
- "?": 11,
13
- "A": 12,
14
- "B": 13,
15
- "C": 14,
16
- "D": 15,
17
- "E": 16,
18
- "F": 17,
19
- "G": 18,
20
- "H": 19,
21
- "I": 20,
22
- "J": 21,
23
- "K": 22,
24
- "L": 23,
25
- "M": 24,
26
- "N": 25,
27
- "O": 26,
28
- "P": 27,
29
- "Q": 28,
30
- "R": 29,
31
- "S": 30,
32
- "T": 31,
33
- "U": 32,
34
- "V": 33,
35
- "W": 34,
36
- "Y": 35,
37
- "Z": 36,
38
- "[PAD]": 50,
39
- "[UNK]": 49,
40
  "|": 0,
41
- "Ç": 37,
42
- "Ö": 38,
43
- "Ü": 39,
44
- "â": 40,
45
- "û": 41,
46
- "İ": 42,
47
- "Ş": 43,
48
- "‘": 44,
49
- "’": 45,
50
- "“": 46,
51
- "”": 47,
52
- "…": 48
53
  }
 
1
  {
2
+ "[PAD]": 37,
3
+ "[UNK]": 36,
4
+ "a": 1,
5
+ "b": 2,
6
+ "c": 3,
7
+ "d": 4,
8
+ "e": 5,
9
+ "f": 6,
10
+ "g": 7,
11
+ "h": 8,
12
+ "i": 9,
13
+ "j": 10,
14
+ "k": 11,
15
+ "l": 12,
16
+ "m": 13,
17
+ "n": 14,
18
+ "o": 15,
19
+ "p": 16,
20
+ "q": 17,
21
+ "r": 18,
22
+ "s": 19,
23
+ "t": 20,
24
+ "u": 21,
25
+ "v": 22,
26
+ "w": 23,
27
+ "x": 24,
28
+ "y": 25,
29
+ "z": 26,
 
 
 
 
 
 
 
 
 
 
30
  "|": 0,
31
+ "â": 27,
32
+ "ç": 28,
33
+ "ö": 29,
34
+ "û": 30,
35
+ "ü": 31,
36
+ "ğ": 32,
37
+ "ı": 33,
38
+ "ş": 34,
39
+ "̇": 35
 
 
 
40
  }