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
c692763
·
verified ·
1 Parent(s): d94d6a6

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -4
  2. tokenizer_config.json +10 -10
  3. vocab.json +41 -39
added_tokens.json CHANGED
@@ -1,6 +1,4 @@
1
  {
2
- "</s>": 43,
3
- "<s>": 42,
4
- "[PAD]": 45,
5
- "[UNK]": 44
6
  }
 
1
  {
2
+ "</s>": 45,
3
+ "<s>": 44
 
 
4
  }
tokenizer_config.json CHANGED
@@ -1,23 +1,23 @@
1
  {
2
  "added_tokens_decoder": {
3
  "42": {
4
- "content": "<s>",
5
- "lstrip": false,
6
  "normalized": false,
7
- "rstrip": false,
8
  "single_word": false,
9
- "special": true
10
  },
11
  "43": {
12
- "content": "</s>",
13
- "lstrip": false,
14
  "normalized": false,
15
- "rstrip": false,
16
  "single_word": false,
17
- "special": true
18
  },
19
  "44": {
20
- "content": "[UNK]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
@@ -25,7 +25,7 @@
25
  "special": true
26
  },
27
  "45": {
28
- "content": "[PAD]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
 
1
  {
2
  "added_tokens_decoder": {
3
  "42": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
  "normalized": false,
7
+ "rstrip": true,
8
  "single_word": false,
9
+ "special": false
10
  },
11
  "43": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
  "normalized": false,
15
+ "rstrip": true,
16
  "single_word": false,
17
+ "special": false
18
  },
19
  "44": {
20
+ "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  },
27
  "45": {
28
+ "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
vocab.json CHANGED
@@ -1,44 +1,46 @@
1
  {
2
- " ": 15,
3
- "a": 35,
4
- "b": 16,
5
- "c": 39,
6
- "d": 5,
7
- "e": 13,
8
- "f": 11,
 
 
9
  "g": 30,
10
- "h": 7,
11
- "i": 20,
12
- "j": 1,
13
- "k": 40,
14
- "l": 25,
15
- "m": 27,
16
- "n": 4,
17
- "o": 33,
18
- "p": 32,
19
- "q": 18,
20
- "r": 38,
21
- "s": 10,
22
- "t": 36,
23
- "u": 24,
24
- "v": 14,
25
- "w": 9,
26
- "x": 8,
27
- "y": 12,
28
- "z": 34,
29
- "á": 23,
30
- "â": 21,
31
- "é": 19,
32
  "î": 28,
33
- "ü": 17,
34
- "ă": 0,
35
- "ć": 3,
36
- "č": 37,
37
- "đ": 29,
38
- "ş": 41,
39
- "š": 31,
40
- "ţ": 22,
41
  "ș": 2,
42
- "ț": 6,
43
- "”": 26
44
  }
 
1
  {
2
+ " ": 20,
3
+ "[PAD]": 43,
4
+ "[UNK]": 42,
5
+ "a": 9,
6
+ "b": 25,
7
+ "c": 32,
8
+ "d": 16,
9
+ "e": 15,
10
+ "f": 21,
11
  "g": 30,
12
+ "h": 13,
13
+ "i": 37,
14
+ "j": 41,
15
+ "k": 29,
16
+ "l": 23,
17
+ "m": 34,
18
+ "n": 38,
19
+ "o": 27,
20
+ "p": 12,
21
+ "q": 33,
22
+ "r": 11,
23
+ "s": 18,
24
+ "t": 22,
25
+ "u": 6,
26
+ "v": 35,
27
+ "w": 0,
28
+ "x": 1,
29
+ "y": 8,
30
+ "z": 4,
31
+ "á": 19,
32
+ "â": 31,
33
+ "é": 24,
34
  "î": 28,
35
+ "ü": 14,
36
+ "ă": 5,
37
+ "ć": 40,
38
+ "č": 3,
39
+ "đ": 7,
40
+ "ş": 17,
41
+ "š": 39,
42
+ "ţ": 10,
43
  "ș": 2,
44
+ "ț": 26,
45
+ "”": 36
46
  }