ashe194 commited on
Commit
7a3bc6b
1 Parent(s): 4030585

Added language model

Browse files
alphabet.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"labels": ["", "<s>", "</s>", "\u2047", " ", "E", "T", "A", "O", "N", "I", "H", "S", "R", "D", "L", "U", "M", "W", "C", "F", "G", "Y", "P", "B", "V", "K", "'", "X", "J", "Q", "Z"], "is_bpe": false}
language_model/3gram_uppercase_correct.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59de0899e9f2f16baeea545e19861478cdb91d8dd2abad4b0f28f94e4c4d6146
3
+ size 46956081
language_model/attrs.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}
language_model/unigrams.txt ADDED
File without changes
preprocessor_config.json CHANGED
@@ -4,7 +4,7 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
7
- "processor_class": "Wav2Vec2Processor",
8
  "return_attention_mask": false,
9
  "sampling_rate": 16000
10
  }
 
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2ProcessorWithLM",
8
  "return_attention_mask": false,
9
  "sampling_rate": 16000
10
  }
special_tokens_map.json CHANGED
@@ -1,6 +1,30 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "pad_token": "<pad>",
5
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": true,
5
+ "normalized": false,
6
+ "rstrip": true,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": true,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
  }
tokenizer_config.json CHANGED
@@ -40,7 +40,7 @@
40
  "eos_token": "</s>",
41
  "model_max_length": 1000000000000000019884624838656,
42
  "pad_token": "<pad>",
43
- "processor_class": "Wav2Vec2Processor",
44
  "replace_word_delimiter_char": " ",
45
  "return_attention_mask": false,
46
  "target_lang": null,
 
40
  "eos_token": "</s>",
41
  "model_max_length": 1000000000000000019884624838656,
42
  "pad_token": "<pad>",
43
+ "processor_class": "Wav2Vec2ProcessorWithLM",
44
  "replace_word_delimiter_char": " ",
45
  "return_attention_mask": false,
46
  "target_lang": null,