Hugging Face's logo

Messam174
/
wav2vec2-large-xls-r-300m-en

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Messam174 commited on
Commit
2bc3968
•
1 Parent(s): 7aab317

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer_config.json +35 -0
  2. vocab.json +26 -26
tokenizer_config.json CHANGED
@@ -1,4 +1,38 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "<s>",
3
  "clean_up_tokenization_spaces": true,
4
  "do_lower_case": false,
@@ -6,6 +40,7 @@
6
  "model_max_length": 1000000000000000019884624838656,
7
  "pad_token": "[PAD]",
8
  "replace_word_delimiter_char": " ",
 
9
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
  "unk_token": "[UNK]",
11
  "word_delimiter_token": "|"
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "27": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "28": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "29": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "30": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
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,
 
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": "|"
vocab.json CHANGED
@@ -1,31 +1,31 @@
1
  {
2
  "[PAD]": 28,
3
  "[UNK]": 27,
4
- "a": 16,
5
- "b": 1,
6
- "c": 18,
7
- "d": 9,
8
- "e": 14,
9
- "f": 0,
10
- "g": 25,
11
- "h": 3,
12
- "i": 24,
13
- "j": 4,
14
- "k": 11,
15
- "l": 12,
16
- "m": 5,
17
  "n": 22,
18
- "o": 23,
19
- "p": 21,
20
- "q": 19,
21
- "r": 10,
22
- "s": 7,
23
- "t": 6,
24
- "u": 20,
25
- "v": 26,
26
- "w": 13,
27
- "x": 15,
28
- "y": 17,
29
- "z": 8,
30
- "|": 2
31
  }
 
1
  {
2
  "[PAD]": 28,
3
  "[UNK]": 27,
4
+ "a": 0,
5
+ "b": 14,
6
+ "c": 7,
7
+ "d": 23,
8
+ "e": 12,
9
+ "f": 4,
10
+ "g": 15,
11
+ "h": 26,
12
+ "i": 1,
13
+ "j": 3,
14
+ "k": 20,
15
+ "l": 9,
16
+ "m": 21,
17
  "n": 22,
18
+ "o": 6,
19
+ "p": 10,
20
+ "q": 25,
21
+ "r": 19,
22
+ "s": 16,
23
+ "t": 11,
24
+ "u": 8,
25
+ "v": 13,
26
+ "w": 2,
27
+ "x": 5,
28
+ "y": 24,
29
+ "z": 18,
30
+ "|": 17
31
  }