gweltou commited on
Commit
eac3a78
1 Parent(s): fccbeb4

Upload tokenizer

Browse files
Files changed (4) hide show
  1. README.md +5 -5
  2. added_tokens.json +2 -2
  3. tokenizer_config.json +6 -6
  4. vocab.json +39 -38
README.md CHANGED
@@ -1,17 +1,17 @@
1
  ---
 
 
2
  license: apache-2.0
3
- base_model: facebook/wav2vec2-xls-r-300m
4
  tags:
5
  - generated_from_trainer
 
 
 
6
  metrics:
7
  - wer
8
  model-index:
9
  - name: wav2vec2-xls-r-300m-breton
10
  results: []
11
- datasets:
12
- - mozilla-foundation/common_voice_15_0
13
- language:
14
- - br
15
  ---
16
 
17
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
1
  ---
2
+ language:
3
+ - br
4
  license: apache-2.0
 
5
  tags:
6
  - generated_from_trainer
7
+ base_model: facebook/wav2vec2-xls-r-300m
8
+ datasets:
9
+ - mozilla-foundation/common_voice_15_0
10
  metrics:
11
  - wer
12
  model-index:
13
  - name: wav2vec2-xls-r-300m-breton
14
  results: []
 
 
 
 
15
  ---
16
 
17
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 40,
3
- "<s>": 39
4
  }
 
1
  {
2
+ "</s>": 41,
3
+ "<s>": 40
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "37": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "38": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,18 +16,18 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "39": {
20
  "content": "<s>",
21
  "lstrip": false,
22
- "normalized": true,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
- "40": {
28
  "content": "</s>",
29
  "lstrip": false,
30
- "normalized": true,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
 
1
  {
2
  "added_tokens_decoder": {
3
+ "38": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "39": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "40": {
20
  "content": "<s>",
21
  "lstrip": false,
22
+ "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "41": {
28
  "content": "</s>",
29
  "lstrip": false,
30
+ "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
vocab.json CHANGED
@@ -1,41 +1,42 @@
1
  {
2
- "'": 15,
3
- "[PAD]": 38,
4
- "[UNK]": 37,
5
- "a": 13,
6
- "b": 35,
7
- "c": 23,
8
- "d": 2,
9
- "e": 32,
10
- "f": 26,
11
- "g": 33,
12
- "h": 1,
13
- "i": 5,
14
- "j": 11,
15
- "k": 28,
16
- "l": 21,
17
- "m": 30,
18
- "n": 25,
19
- "o": 19,
20
- "p": 10,
21
- "q": 8,
22
- "r": 27,
23
- "s": 29,
24
- "t": 12,
25
- "u": 17,
26
- "v": 3,
27
- "w": 4,
28
- "x": 31,
29
  "y": 7,
30
- "z": 16,
31
- "|": 0,
32
- "à": 20,
33
- "â": 14,
34
- "è": 18,
35
- "é": 24,
36
- "ê": 6,
37
- "ñ": 22,
38
- "ô": 9,
39
- "ù": 36,
40
- "ü": 34
 
41
  }
 
1
  {
2
+ "'": 23,
3
+ "[PAD]": 39,
4
+ "[UNK]": 38,
5
+ "a": 9,
6
+ "b": 3,
7
+ "c": 1,
8
+ "d": 15,
9
+ "e": 13,
10
+ "f": 32,
11
+ "g": 37,
12
+ "h": 16,
13
+ "i": 33,
14
+ "j": 36,
15
+ "k": 6,
16
+ "l": 34,
17
+ "m": 29,
18
+ "n": 11,
19
+ "o": 27,
20
+ "p": 31,
21
+ "q": 12,
22
+ "r": 0,
23
+ "s": 22,
24
+ "t": 14,
25
+ "u": 28,
26
+ "v": 2,
27
+ "w": 26,
28
+ "x": 19,
29
  "y": 7,
30
+ "z": 10,
31
+ "|": 5,
32
+ "à": 21,
33
+ "â": 20,
34
+ "è": 24,
35
+ "é": 25,
36
+ "ê": 17,
37
+ "ñ": 4,
38
+ "ô": 35,
39
+ "ù": 8,
40
+ "û": 30,
41
+ "ü": 18
42
  }