Hugging Face's logo

AdaCodruta
/
wav2vec2-romanian-test

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
AdaCodruta commited on
Commit
d94d6a6
•
1 Parent(s): a06471c

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -4
  2. special_tokens_map.json +2 -2
  3. tokenizer_config.json +7 -23
  4. vocab.json +42 -44
added_tokens.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "</s>": 45,
3
- "<pad>": 47,
4
- "<s>": 44,
5
- "<unk>": 46
6
  }
 
1
  {
2
+ "</s>": 43,
3
+ "<s>": 42,
4
+ "[PAD]": 45,
5
+ "[UNK]": 44
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
@@ -1,22 +1,6 @@
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,
@@ -24,7 +8,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "45": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,16 +16,16 @@
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,
@@ -54,10 +38,10 @@
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
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "42": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "content": "<s>",
5
  "lstrip": false,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "43": {
12
  "content": "</s>",
13
  "lstrip": false,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "44": {
20
+ "content": "[UNK]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "45": {
28
+ "content": "[PAD]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
 
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
  }
vocab.json CHANGED
@@ -1,46 +1,44 @@
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
  }
 
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
  }