Hugging Face's logo

wandererupak
/
wave2vec-bert-infinity-solution-found-prepare-dataset-problem-check-finally

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2-bert
Model card Files
xet
Community
wandererupak commited on
Commit
bcd115f
·
verified ·
1 Parent(s): 8d3e498

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +2 -3
  3. vocab.json +5 -3
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 63,
3
- "<s>": 62
4
  }
 
1
  {
2
+ "</s>": 65,
3
+ "<s>": 64
4
  }
tokenizer_config.json CHANGED
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "62": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "63": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": 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",
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "64": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "65": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": 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
@@ -58,7 +58,9 @@
58
  "ृ": 56,
59
  "े": 57,
60
  "ै": 58,
61
- "ो": 59,
62
- "ौ": 60,
63
- "्": 61
 
 
64
  }
 
58
  "ृ": 56,
59
  "े": 57,
60
  "ै": 58,
61
+ "ॊ": 59,
62
+ "ो": 60,
63
+ "ौ": 61,
64
+ "्": 62,
65
+ "ॠ": 63
66
  }