Hugging Face's logo

EzraWilliam
/
wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
EzraWilliam commited on
Commit
09bfc59
•
1 Parent(s): 8924635

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +1 -3
  2. tokenizer_config.json +34 -0
  3. vocab.json +28 -28
added_tokens.json CHANGED
@@ -1,6 +1,4 @@
1
  {
2
  "</s>": 32,
3
- "<s>": 31,
4
- "[PAD]": 30,
5
- "[UNK]": 29
6
  }
 
1
  {
2
  "</s>": 32,
3
+ "<s>": 31
 
 
4
  }
tokenizer_config.json CHANGED
@@ -1,4 +1,38 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "<s>",
3
  "clean_up_tokenization_spaces": true,
4
  "do_lower_case": false,
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "29": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "30": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "31": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
  "bos_token": "<s>",
37
  "clean_up_tokenization_spaces": true,
38
  "do_lower_case": false,
vocab.json CHANGED
@@ -1,33 +1,33 @@
1
  {
2
- "\"": 24,
3
- "'": 16,
4
  "[PAD]": 30,
5
  "[UNK]": 29,
6
- "a": 11,
7
- "b": 20,
8
- "c": 4,
9
- "d": 9,
10
- "e": 23,
11
- "f": 1,
12
- "g": 5,
13
  "h": 12,
14
- "i": 13,
15
- "j": 27,
16
- "k": 22,
17
- "l": 28,
18
- "m": 14,
19
- "n": 10,
20
- "o": 21,
21
- "p": 17,
22
- "q": 25,
23
- "r": 0,
24
- "s": 6,
25
- "t": 8,
26
- "u": 3,
27
- "v": 7,
28
- "w": 2,
29
- "x": 19,
30
- "y": 15,
31
- "z": 26,
32
- "|": 18
33
  }
 
1
  {
2
+ "\"": 3,
3
+ "'": 22,
4
  "[PAD]": 30,
5
  "[UNK]": 29,
6
+ "a": 27,
7
+ "b": 11,
8
+ "c": 17,
9
+ "d": 2,
10
+ "e": 20,
11
+ "f": 18,
12
+ "g": 4,
13
  "h": 12,
14
+ "i": 1,
15
+ "j": 24,
16
+ "k": 10,
17
+ "l": 26,
18
+ "m": 28,
19
+ "n": 0,
20
+ "o": 9,
21
+ "p": 8,
22
+ "q": 6,
23
+ "r": 5,
24
+ "s": 25,
25
+ "t": 15,
26
+ "u": 7,
27
+ "v": 19,
28
+ "w": 16,
29
+ "x": 14,
30
+ "y": 23,
31
+ "z": 21,
32
+ "|": 13
33
  }