Hugging Face's logo

asr-africa
/
w2v2-bert-wolof-kallaama-42-hours

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2-bert
Generated from Trainer
Inference Endpoints
Model card Files Community
dmusingu commited on
Commit
4a1d18b
·
verified ·
1 Parent(s): 1c4c8c0

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -4
  2. tokenizer_config.json +10 -11
  3. vocab.json +3 -1
added_tokens.json CHANGED
@@ -1,6 +1,4 @@
1
  {
2
- "</s>": 48,
3
- "<s>": 47,
4
- "[PAD]": 50,
5
- "[UNK]": 49
6
  }
 
1
  {
2
+ "</s>": 50,
3
+ "<s>": 49
 
 
4
  }
tokenizer_config.json CHANGED
@@ -1,23 +1,23 @@
1
  {
2
  "added_tokens_decoder": {
3
  "47": {
4
- "content": "<s>",
5
- "lstrip": false,
6
  "normalized": false,
7
- "rstrip": false,
8
  "single_word": false,
9
- "special": true
10
  },
11
  "48": {
12
- "content": "</s>",
13
- "lstrip": false,
14
  "normalized": false,
15
- "rstrip": false,
16
  "single_word": false,
17
- "special": true
18
  },
19
  "49": {
20
- "content": "[UNK]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
@@ -25,7 +25,7 @@
25
  "special": true
26
  },
27
  "50": {
28
- "content": "[PAD]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
@@ -40,7 +40,6 @@
40
  "extra_special_tokens": {},
41
  "model_max_length": 1000000000000000019884624838656,
42
  "pad_token": "[PAD]",
43
- "processor_class": "Wav2Vec2BertProcessor",
44
  "replace_word_delimiter_char": " ",
45
  "target_lang": null,
46
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
1
  {
2
  "added_tokens_decoder": {
3
  "47": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
  "normalized": false,
7
+ "rstrip": true,
8
  "single_word": false,
9
+ "special": false
10
  },
11
  "48": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
  "normalized": false,
15
+ "rstrip": true,
16
  "single_word": false,
17
+ "special": false
18
  },
19
  "49": {
20
+ "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  },
27
  "50": {
28
+ "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
 
40
  "extra_special_tokens": {},
41
  "model_max_length": 1000000000000000019884624838656,
42
  "pad_token": "[PAD]",
 
43
  "replace_word_delimiter_char": " ",
44
  "target_lang": null,
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
vocab.json CHANGED
@@ -1,5 +1,6 @@
1
  {
2
- " ": 0,
 
3
  "a": 1,
4
  "b": 2,
5
  "c": 3,
@@ -26,6 +27,7 @@
26
  "x": 24,
27
  "y": 25,
28
  "z": 26,
 
29
  "à": 27,
30
  "á": 28,
31
  "â": 29,
 
1
  {
2
+ "[PAD]": 48,
3
+ "[UNK]": 47,
4
  "a": 1,
5
  "b": 2,
6
  "c": 3,
 
27
  "x": 24,
28
  "y": 25,
29
  "z": 26,
30
+ "|": 0,
31
  "à": 27,
32
  "á": 28,
33
  "â": 29,