Hugging Face's logo

AdaCodruta
/
wav2vec2_common_voice17_finetuning

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
AdaCodruta commited on
Commit
a06471c
·
verified ·
1 Parent(s): f688496

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +3 -1
  2. special_tokens_map.json +2 -2
  3. tokenizer_config.json +18 -2
  4. vocab.json +42 -42
added_tokens.json CHANGED
@@ -1,4 +1,6 @@
1
  {
2
  "</s>": 45,
3
- "<s>": 44
 
 
4
  }
 
1
  {
2
  "</s>": 45,
3
+ "<pad>": 47,
4
+ "<s>": 44,
5
+ "<unk>": 46
6
  }
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
@@ -31,6 +31,22 @@
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  }
35
  },
36
  "bos_token": "<s>",
@@ -38,10 +54,10 @@
38
  "do_lower_case": 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",
45
- "unk_token": "[UNK]",
46
  "word_delimiter_token": "|"
47
  }
 
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
+ },
35
+ "46": {
36
+ "content": "<unk>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "47": {
44
+ "content": "<pad>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
  }
51
  },
52
  "bos_token": "<s>",
 
54
  "do_lower_case": false,
55
  "eos_token": "</s>",
56
  "model_max_length": 1000000000000000019884624838656,
57
+ "pad_token": "<pad>",
58
  "replace_word_delimiter_char": " ",
59
  "target_lang": null,
60
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
61
+ "unk_token": "<unk>",
62
  "word_delimiter_token": "|"
63
  }
vocab.json CHANGED
@@ -1,46 +1,46 @@
1
  {
2
- " ": 1,
3
  "[PAD]": 43,
4
  "[UNK]": 42,
5
- "a": 41,
6
- "b": 4,
7
- "c": 2,
8
- "d": 20,
9
- "e": 28,
10
- "f": 30,
11
- "g": 8,
12
- "h": 32,
13
- "i": 18,
14
- "j": 17,
15
- "k": 16,
16
- "l": 15,
17
- "m": 39,
18
- "n": 13,
19
- "o": 3,
20
- "p": 35,
21
- "q": 27,
22
- "r": 24,
23
- "s": 38,
24
- "t": 26,
25
- "u": 34,
26
- "v": 33,
27
- "w": 9,
28
- "x": 40,
29
- "y": 19,
30
- "z": 7,
31
- "á": 22,
32
- "â": 14,
33
- "é": 11,
34
- "î": 5,
35
- "ü": 25,
36
- "ă": 0,
37
- "ć": 12,
38
- "č": 29,
39
- "đ": 23,
40
- "ş": 37,
41
- "š": 6,
42
- "ţ": 31,
43
- "ș": 36,
44
- "ț": 10,
45
- "”": 21
46
  }
 
1
  {
2
+ " ": 2,
3
  "[PAD]": 43,
4
  "[UNK]": 42,
5
+ "a": 11,
6
+ "b": 1,
7
+ "c": 14,
8
+ "d": 16,
9
+ "e": 41,
10
+ "f": 39,
11
+ "g": 20,
12
+ "h": 28,
13
+ "i": 40,
14
+ "j": 31,
15
+ "k": 23,
16
+ "l": 12,
17
+ "m": 5,
18
+ "n": 21,
19
+ "o": 10,
20
+ "p": 9,
21
+ "q": 38,
22
+ "r": 19,
23
+ "s": 15,
24
+ "t": 6,
25
+ "u": 4,
26
+ "v": 8,
27
+ "w": 18,
28
+ "x": 22,
29
+ "y": 37,
30
+ "z": 17,
31
+ "á": 33,
32
+ "â": 30,
33
+ "é": 26,
34
+ "î": 34,
35
+ "ü": 24,
36
+ "ă": 27,
37
+ "ć": 36,
38
+ "č": 0,
39
+ "đ": 7,
40
+ "ş": 3,
41
+ "š": 32,
42
+ "ţ": 25,
43
+ "ș": 13,
44
+ "ț": 29,
45
+ "”": 35
46
  }