Hugging Face's logo

asr-africa
/
bambara-mms-10-hours-oza75bambara-asr-hf

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files Community
dmusingu commited on
Commit
9ce127a
·
verified ·
1 Parent(s): 819f0bf

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -2
  2. special_tokens_map.json +2 -2
  3. tokenizer_config.json +24 -25
  4. vocab.json +0 -0
added_tokens.json CHANGED
@@ -1,4 +1,6 @@
1
  {
2
- "</s>": 43,
3
- "<s>": 42
 
 
4
  }
 
1
  {
2
+ "</s>": 42,
3
+ "<s>": 41,
4
+ "[PAD]": 44,
5
+ "[UNK]": 43
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
@@ -1,48 +1,47 @@
1
  {
2
  "added_tokens_decoder": {
3
- "0": {
4
- "content": "<pad>",
5
- "lstrip": true,
6
  "normalized": false,
7
- "rstrip": true,
8
  "single_word": false,
9
- "special": false
10
  },
11
- "1": {
12
- "content": "<s>",
13
- "lstrip": true,
14
  "normalized": false,
15
- "rstrip": true,
16
  "single_word": false,
17
- "special": false
18
  },
19
- "2": {
20
- "content": "</s>",
21
- "lstrip": true,
22
  "normalized": false,
23
- "rstrip": true,
24
  "single_word": false,
25
- "special": false
26
  },
27
- "3": {
28
- "content": "<unk>",
29
- "lstrip": true,
30
  "normalized": false,
31
- "rstrip": true,
32
  "single_word": false,
33
- "special": false
34
  }
35
  },
36
  "bos_token": "<s>",
37
- "clean_up_tokenization_spaces": true,
38
  "do_lower_case": false,
39
  "eos_token": "</s>",
40
  "model_max_length": 1000000000000000019884624838656,
41
- "pad_token": "<pad>",
42
- "processor_class": "Wav2Vec2Processor",
43
  "replace_word_delimiter_char": " ",
44
- "target_lang": "eng",
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
- "unk_token": "<unk>",
47
  "word_delimiter_token": "|"
48
  }
 
1
  {
2
  "added_tokens_decoder": {
3
+ "41": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
  "normalized": false,
7
+ "rstrip": false,
8
  "single_word": false,
9
+ "special": true
10
  },
11
+ "42": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
  "normalized": false,
15
+ "rstrip": false,
16
  "single_word": false,
17
+ "special": true
18
  },
19
+ "43": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
  "normalized": false,
23
+ "rstrip": false,
24
  "single_word": false,
25
+ "special": true
26
  },
27
+ "44": {
28
+ "content": "[PAD]",
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": 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
The diff for this file is too large to render. See raw diff