Hugging Face's logo

Lakoc
/
DeCRED_small_cv_2

Transformers
Safetensors
joint_aed_ctc_speech-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Community
Lakoc commited on
Commit
cdcca07
•
1 Parent(s): 2df7f66

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +44 -0
  2. tokenizer.json +4144 -0
  3. tokenizer_config.json +61 -0
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "([bos])",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "([eos])",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "([mask])",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "([pad])",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sep_token": {
31
+ "content": "▁",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "([unk])",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
tokenizer.json ADDED
@@ -0,0 +1,4144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "([bos])",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "([eos])",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "([unk])",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "([pad])",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "([mask])",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 8,
53
+ "content": "▁",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ }
60
+ ],
61
+ "normalizer": null,
62
+ "pre_tokenizer": {
63
+ "type": "Metaspace",
64
+ "replacement": "▁",
65
+ "add_prefix_space": true,
66
+ "prepend_scheme": "always"
67
+ },
68
+ "post_processor": {
69
+ "type": "TemplateProcessing",
70
+ "single": [
71
+ {
72
+ "Sequence": {
73
+ "id": "A",
74
+ "type_id": 0
75
+ }
76
+ },
77
+ {
78
+ "SpecialToken": {
79
+ "id": "([eos])",
80
+ "type_id": 0
81
+ }
82
+ }
83
+ ],
84
+ "pair": [
85
+ {
86
+ "Sequence": {
87
+ "id": "A",
88
+ "type_id": 0
89
+ }
90
+ },
91
+ {
92
+ "SpecialToken": {
93
+ "id": "([eos])",
94
+ "type_id": 0
95
+ }
96
+ },
97
+ {
98
+ "Sequence": {
99
+ "id": "B",
100
+ "type_id": 1
101
+ }
102
+ },
103
+ {
104
+ "SpecialToken": {
105
+ "id": "([eos])",
106
+ "type_id": 1
107
+ }
108
+ }
109
+ ],
110
+ "special_tokens": {
111
+ "([bos])": {
112
+ "id": "([bos])",
113
+ "ids": [
114
+ 0
115
+ ],
116
+ "tokens": [
117
+ "([bos])"
118
+ ]
119
+ },
120
+ "([eos])": {
121
+ "id": "([eos])",
122
+ "ids": [
123
+ 1
124
+ ],
125
+ "tokens": [
126
+ "([eos])"
127
+ ]
128
+ }
129
+ }
130
+ },
131
+ "decoder": {
132
+ "type": "Metaspace",
133
+ "replacement": "▁",
134
+ "add_prefix_space": true,
135
+ "prepend_scheme": "always"
136
+ },
137
+ "model": {
138
+ "type": "Unigram",
139
+ "unk_id": 2,
140
+ "vocab": [
141
+ [
142
+ "([bos])",
143
+ 0.0
144
+ ],
145
+ [
146
+ "([eos])",
147
+ 0.0
148
+ ],
149
+ [
150
+ "([unk])",
151
+ 0.0
152
+ ],
153
+ [
154
+ "([pad])",
155
+ 0.0
156
+ ],
157
+ [
158
+ "([mask])",
159
+ 0.0
160
+ ],
161
+ [
162
+ "s",
163
+ -2.7142058517262875
164
+ ],
165
+ [
166
+ "▁the",
167
+ -3.266077726769307
168
+ ],
169
+ [
170
+ "t",
171
+ -3.4681844110225715
172
+ ],
173
+ [
174
+ "▁",
175
+ -3.5045292221545505
176
+ ],
177
+ [
178
+ "e",
179
+ -3.53243604604831
180
+ ],
181
+ [
182
+ "d",
183
+ -3.746795505406471
184
+ ],
185
+ [
186
+ "a",
187
+ -3.966644864782042
188
+ ],
189
+ [
190
+ "▁a",
191
+ -4.045297326782757
192
+ ],
193
+ [
194
+ "ed",
195
+ -4.078676075277873
196
+ ],
197
+ [
198
+ "i",
199
+ -4.082775869080045
200
+ ],
201
+ [
202
+ "n",
203
+ -4.092123175436564
204
+ ],
205
+ [
206
+ "r",
207
+ -4.168281078700067
208
+ ],
209
+ [
210
+ "▁of",
211
+ -4.267933495012722
212
+ ],
213
+ [
214
+ "▁in",
215
+ -4.327956814336762
216
+ ],
217
+ [
218
+ "l",
219
+ -4.346454994977579
220
+ ],
221
+ [
222
+ "▁to",
223
+ -4.542642082528419
224
+ ],
225
+ [
226
+ "y",
227
+ -4.547846816375564
228
+ ],
229
+ [
230
+ "▁is",
231
+ -4.561382632099523
232
+ ],
233
+ [
234
+ "o",
235
+ -4.564814277299618
236
+ ],
237
+ [
238
+ "ing",
239
+ -4.5768138723470955
240
+ ],
241
+ [
242
+ "▁and",
243
+ -4.582373336093488
244
+ ],
245
+ [
246
+ "▁was",
247
+ -4.767419810016145
248
+ ],
249
+ [
250
+ "m",
251
+ -4.94726376910474
252
+ ],
253
+ [
254
+ "▁he",
255
+ -4.974815241685285
256
+ ],
257
+ [
258
+ "c",
259
+ -5.022225255873906
260
+ ],
261
+ [
262
+ "er",
263
+ -5.036810038674725
264
+ ],
265
+ [
266
+ "p",
267
+ -5.060332470938388
268
+ ],
269
+ [
270
+ "b",
271
+ -5.068433510800604
272
+ ],
273
+ [
274
+ "in",
275
+ -5.15900035344338
276
+ ],
277
+ [
278
+ "ly",
279
+ -5.193847645206915
280
+ ],
281
+ [
282
+ "▁it",
283
+ -5.215618381775846
284
+ ],
285
+ [
286
+ "f",
287
+ -5.2711163831213685
288
+ ],
289
+ [
290
+ "al",
291
+ -5.301249758864202
292
+ ],
293
+ [
294
+ "or",
295
+ -5.312048292929285
296
+ ],
297
+ [
298
+ "▁be",
299
+ -5.3344236780927545
300
+ ],
301
+ [
302
+ "▁for",
303
+ -5.354847011896672
304
+ ],
305
+ [
306
+ "▁re",
307
+ -5.430822952843879
308
+ ],
309
+ [
310
+ "g",
311
+ -5.446659545835704
312
+ ],
313
+ [
314
+ "u",
315
+ -5.449209803829399
316
+ ],
317
+ [
318
+ "an",
319
+ -5.461456262180917
320
+ ],
321
+ [
322
+ "le",
323
+ -5.485306773836843
324
+ ],
325
+ [
326
+ "w",
327
+ -5.50802990965715
328
+ ],
329
+ [
330
+ "ar",
331
+ -5.523425129847167
332
+ ],
333
+ [
334
+ "re",
335
+ -5.564005312911405
336
+ ],
337
+ [
338
+ "▁are",
339
+ -5.585534202380469
340
+ ],
341
+ [
342
+ "h",
343
+ -5.6644928360782245
344
+ ],
345
+ [
346
+ "-",
347
+ -5.670696987962916
348
+ ],
349
+ [
350
+ "k",
351
+ -5.678877446917772
352
+ ],
353
+ [
354
+ "▁on",
355
+ -5.687817643627447
356
+ ],
357
+ [
358
+ "en",
359
+ -5.715569650173016
360
+ ],
361
+ [
362
+ "▁his",
363
+ -5.72049064645074
364
+ ],
365
+ [
366
+ "ic",
367
+ -5.732452984995662
368
+ ],
369
+ [
370
+ "▁by",
371
+ -5.73361521100181
372
+ ],
373
+ [
374
+ "on",
375
+ -5.745444310105055
376
+ ],
377
+ [
378
+ "▁with",
379
+ -5.745727056090052
380
+ ],
381
+ [
382
+ "▁this",
383
+ -5.7852743858084335
384
+ ],
385
+ [
386
+ "▁also",
387
+ -5.789222886415049
388
+ ],
389
+ [
390
+ "is",
391
+ -5.791623269794124
392
+ ],
393
+ [
394
+ "it",
395
+ -5.838030009896425
396
+ ],
397
+ [
398
+ "▁as",
399
+ -5.950372775660929
400
+ ],
401
+ [
402
+ "th",
403
+ -5.961565786912297
404
+ ],
405
+ [
406
+ "▁an",
407
+ -5.987225115194679
408
+ ],
409
+ [
410
+ "ch",
411
+ -6.00110634144939
412
+ ],
413
+ [
414
+ "ce",
415
+ -6.005579943200157
416
+ ],
417
+ [
418
+ "ation",
419
+ -6.016209515041735
420
+ ],
421
+ [
422
+ "▁de",
423
+ -6.024326469068459
424
+ ],
425
+ [
426
+ "▁were",
427
+ -6.120402098115683
428
+ ],
429
+ [
430
+ "ck",
431
+ -6.13570396348357
432
+ ],
433
+ [
434
+ "▁has",
435
+ -6.1604740749733615
436
+ ],
437
+ [
438
+ "▁at",
439
+ -6.1665615024086815
440
+ ],
441
+ [
442
+ "▁con",
443
+ -6.171395914280048
444
+ ],
445
+ [
446
+ "ter",
447
+ -6.178357796176943
448
+ ],
449
+ [
450
+ "▁pa",
451
+ -6.184579472989292
452
+ ],
453
+ [
454
+ "▁di",
455
+ -6.192506491397001
456
+ ],
457
+ [
458
+ "▁from",
459
+ -6.2274963476148155
460
+ ],
461
+ [
462
+ "z",
463
+ -6.233832656471341
464
+ ],
465
+ [
466
+ "▁that",
467
+ -6.259145222689275
468
+ ],
469
+ [
470
+ "▁she",
471
+ -6.261823071383178
472
+ ],
473
+ [
474
+ "ent",
475
+ -6.273559485076177
476
+ ],
477
+ [
478
+ "ve",
479
+ -6.287745527877524
480
+ ],
481
+ [
482
+ "ll",
483
+ -6.296934130149953
484
+ ],
485
+ [
486
+ "ion",
487
+ -6.303428379883117
488
+ ],
489
+ [
490
+ "ur",
491
+ -6.3407337786835125
492
+ ],
493
+ [
494
+ "▁not",
495
+ -6.346123894928427
496
+ ],
497
+ [
498
+ "▁ro",
499
+ -6.378132550002775
500
+ ],
501
+ [
502
+ "▁me",
503
+ -6.3892165501912395
504
+ ],
505
+ [
506
+ "us",
507
+ -6.393408207350147
508
+ ],
509
+ [
510
+ "ate",
511
+ -6.404987541552584
512
+ ],
513
+ [
514
+ "ge",
515
+ -6.407969713535913
516
+ ],
517
+ [
518
+ "▁se",
519
+ -6.417440557255812
520
+ ],
521
+ [
522
+ "▁c",
523
+ -6.428010656832997
524
+ ],
525
+ [
526
+ "x",
527
+ -6.428867114215537
528
+ ],
529
+ [
530
+ "ment",
531
+ -6.4427680144962345
532
+ ],
533
+ [
534
+ "est",
535
+ -6.442833858954188
536
+ ],
537
+ [
538
+ "▁i",
539
+ -6.4466213063191145
540
+ ],
541
+ [
542
+ "v",
543
+ -6.4606981545382105
544
+ ],
545
+ [
546
+ "▁ho",
547
+ -6.4783104949578245
548
+ ],
549
+ [
550
+ "▁ma",
551
+ -6.498125017152299
552
+ ],
553
+ [
554
+ "▁do",
555
+ -6.501752446265398
556
+ ],
557
+ [
558
+ "▁her",
559
+ -6.515398164184424
560
+ ],
561
+ [
562
+ "▁bo",
563
+ -6.522430744871071
564
+ ],
565
+ [
566
+ "im",
567
+ -6.53403598402163
568
+ ],
569
+ [
570
+ "▁no",
571
+ -6.534558554272426
572
+ ],
573
+ [
574
+ "▁have",
575
+ -6.5685136086251585
576
+ ],
577
+ [
578
+ "▁two",
579
+ -6.575123668331273
580
+ ],
581
+ [
582
+ "▁co",
583
+ -6.591894918105922
584
+ ],
585
+ [
586
+ "▁k",
587
+ -6.606856421143078
588
+ ],
589
+ [
590
+ "ver",
591
+ -6.607525875982011
592
+ ],
593
+ [
594
+ "▁fa",
595
+ -6.613660208245481
596
+ ],
597
+ [
598
+ "▁ba",
599
+ -6.615313155284893
600
+ ],
601
+ [
602
+ "at",
603
+ -6.625740611824233
604
+ ],
605
+ [
606
+ "▁ex",
607
+ -6.62637779295275
608
+ ],
609
+ [
610
+ "▁ra",
611
+ -6.628800941363236
612
+ ],
613
+ [
614
+ "ry",
615
+ -6.653214733681473
616
+ ],
617
+ [
618
+ "▁all",
619
+ -6.66469564745948
620
+ ],
621
+ [
622
+ "▁there",
623
+ -6.66844118808865
624
+ ],
625
+ [
626
+ "▁mo",
627
+ -6.67106236533283
628
+ ],
629
+ [
630
+ "am",
631
+ -6.676242636979339
632
+ ],
633
+ [
634
+ "▁they",
635
+ -6.677178799395
636
+ ],
637
+ [
638
+ "▁one",
639
+ -6.677384225117864
640
+ ],
641
+ [
642
+ "▁can",
643
+ -6.681420059563639
644
+ ],
645
+ [
646
+ "vi",
647
+ -6.709959752152264
648
+ ],
649
+ [
650
+ "lo",
651
+ -6.713154281118065
652
+ ],
653
+ [
654
+ "ow",
655
+ -6.723831218437194
656
+ ],
657
+ [
658
+ "▁fi",
659
+ -6.726589216495869
660
+ ],
661
+ [
662
+ "▁pro",
663
+ -6.7314450012561
664
+ ],
665
+ [
666
+ "▁ha",
667
+ -6.749209503748762
668
+ ],
669
+ [
670
+ "▁ch",
671
+ -6.772095921880828
672
+ ],
673
+ [
674
+ "▁or",
675
+ -6.776365650103081
676
+ ],
677
+ [
678
+ "▁sp",
679
+ -6.786393276062583
680
+ ],
681
+ [
682
+ "▁had",
683
+ -6.79223049765579
684
+ ],
685
+ [
686
+ "▁la",
687
+ -6.795382351097437
688
+ ],
689
+ [
690
+ "ke",
691
+ -6.800168033699109
692
+ ],
693
+ [
694
+ "▁su",
695
+ -6.800774748957359
696
+ ],
697
+ [
698
+ "ies",
699
+ -6.810016118434552
700
+ ],
701
+ [
702
+ "ers",
703
+ -6.812082064826704
704
+ ],
705
+ [
706
+ "ive",
707
+ -6.81569606544878
708
+ ],
709
+ [
710
+ "▁mi",
711
+ -6.821300864111514
712
+ ],
713
+ [
714
+ "▁lo",
715
+ -6.825339535971379
716
+ ],
717
+ [
718
+ "ated",
719
+ -6.825595609411938
720
+ ],
721
+ [
722
+ "ian",
723
+ -6.8258488952010925
724
+ ],
725
+ [
726
+ "me",
727
+ -6.827060831018173
728
+ ],
729
+ [
730
+ "▁part",
731
+ -6.831319323934572
732
+ ],
733
+ [
734
+ "▁un",
735
+ -6.834647079614271
736
+ ],
737
+ [
738
+ "▁so",
739
+ -6.840942547772675
740
+ ],
741
+ [
742
+ "tion",
743
+ -6.845914749541093
744
+ ],
745
+ [
746
+ "▁after",
747
+ -6.84985564767894
748
+ ],
749
+ [
750
+ "▁po",
751
+ -6.857737040629791
752
+ ],
753
+ [
754
+ "▁been",
755
+ -6.859188228545115
756
+ ],
757
+ [
758
+ "▁first",
759
+ -6.861598581896203
760
+ ],
761
+ [
762
+ "tic",
763
+ -6.878762521429671
764
+ ],
765
+ [
766
+ "om",
767
+ -6.883129570248538
768
+ ],
769
+ [
770
+ "▁new",
771
+ -6.896230592082377
772
+ ],
773
+ [
774
+ "▁school",
775
+ -6.905097652791072
776
+ ],
777
+ [
778
+ "um",
779
+ -6.9090275544645525
780
+ ],
781
+ [
782
+ "▁their",
783
+ -6.912734101387549
784
+ ],
785
+ [
786
+ "▁sc",
787
+ -6.933326754224046
788
+ ],
789
+ [
790
+ "▁its",
791
+ -6.937682807122778
792
+ ],
793
+ [
794
+ "▁le",
795
+ -6.940358887201773
796
+ ],
797
+ [
798
+ "▁w",
799
+ -6.940842423851915
800
+ ],
801
+ [
802
+ "ul",
803
+ -6.94110827313745
804
+ ],
805
+ [
806
+ "▁work",
807
+ -6.949677715478737
808
+ ],
809
+ [
810
+ "▁other",
811
+ -6.9523598336439125
812
+ ],
813
+ [
814
+ "▁we",
815
+ -6.95346715825179
816
+ ],
817
+ [
818
+ "ut",
819
+ -6.960916166059883
820
+ ],
821
+ [
822
+ "man",
823
+ -6.964884341526368
824
+ ],
825
+ [
826
+ "▁some",
827
+ -6.977696078158498
828
+ ],
829
+ [
830
+ "un",
831
+ -6.979877324440615
832
+ ],
833
+ [
834
+ "▁time",
835
+ -6.986570441870228
836
+ ],
837
+ [
838
+ "▁ca",
839
+ -6.988490157320621
840
+ ],
841
+ [
842
+ "▁you",
843
+ -6.99639882428054
844
+ ],
845
+ [
846
+ "ance",
847
+ -6.999274442223426
848
+ ],
849
+ [
850
+ "▁play",
851
+ -7.002502888833199
852
+ ],
853
+ [
854
+ "▁go",
855
+ -7.004466016906287
856
+ ],
857
+ [
858
+ "▁li",
859
+ -7.007368121818985
860
+ ],
861
+ [
862
+ "ity",
863
+ -7.021854561852786
864
+ ],
865
+ [
866
+ "ng",
867
+ -7.043741300457798
868
+ ],
869
+ [
870
+ "ton",
871
+ -7.044389861055102
872
+ ],
873
+ [
874
+ "ard",
875
+ -7.052742092697903
876
+ ],
877
+ [
878
+ "ma",
879
+ -7.053038033509955
880
+ ],
881
+ [
882
+ "op",
883
+ -7.0555392015014196
884
+ ],
885
+ [
886
+ "▁com",
887
+ -7.060523474132848
888
+ ],
889
+ [
890
+ "▁sta",
891
+ -7.072938466920112
892
+ ],
893
+ [
894
+ "▁fl",
895
+ -7.093443929951222
896
+ ],
897
+ [
898
+ "▁bi",
899
+ -7.094392877971398
900
+ ],
901
+ [
902
+ "mp",
903
+ -7.100070525723389
904
+ ],
905
+ [
906
+ "▁these",
907
+ -7.105941098155345
908
+ ],
909
+ [
910
+ "▁but",
911
+ -7.106296726596112
912
+ ],
913
+ [
914
+ "vo",
915
+ -7.1077544081210995
916
+ ],
917
+ [
918
+ "ide",
919
+ -7.108633982065594
920
+ ],
921
+ [
922
+ "▁car",
923
+ -7.1088530750515595
924
+ ],
925
+ [
926
+ "▁up",
927
+ -7.109501518373792
928
+ ],
929
+ [
930
+ "age",
931
+ -7.114556836092426
932
+ ],
933
+ [
934
+ "if",
935
+ -7.118715610465305
936
+ ],
937
+ [
938
+ "▁pre",
939
+ -7.126244139579125
940
+ ],
941
+ [
942
+ "ence",
943
+ -7.141668416831232
944
+ ],
945
+ [
946
+ "▁most",
947
+ -7.145628418047821
948
+ ],
949
+ [
950
+ "▁later",
951
+ -7.151336704475602
952
+ ],
953
+ [
954
+ "▁cl",
955
+ -7.151458790940525
956
+ ],
957
+ [
958
+ "ber",
959
+ -7.156518168649448
960
+ ],
961
+ [
962
+ "co",
963
+ -7.171591273376702
964
+ ],
965
+ [
966
+ "▁many",
967
+ -7.173579097459429
968
+ ],
969
+ [
970
+ "▁th",
971
+ -7.176175909519051
972
+ ],
973
+ [
974
+ "▁comp",
975
+ -7.177138295798342
976
+ ],
977
+ [
978
+ "▁bu",
979
+ -7.179756301325936
980
+ ],
981
+ [
982
+ "▁pi",
983
+ -7.187954413412804
984
+ ],
985
+ [
986
+ "ell",
987
+ -7.188247059066965
988
+ ],
989
+ [
990
+ "per",
991
+ -7.200276230714959
992
+ ],
993
+ [
994
+ "able",
995
+ -7.200683922295507
996
+ ],
997
+ [
998
+ "▁him",
999
+ -7.20131847471121
1000
+ ],
1001
+ [
1002
+ "▁mar",
1003
+ -7.212074763797912
1004
+ ],
1005
+ [
1006
+ "lu",
1007
+ -7.2142484300898495
1008
+ ],
1009
+ [
1010
+ "▁sh",
1011
+ -7.22127923539019
1012
+ ],
1013
+ [
1014
+ "ight",
1015
+ -7.222925534341611
1016
+ ],
1017
+ [
1018
+ "▁ne",
1019
+ -7.225806940112452
1020
+ ],
1021
+ [
1022
+ "▁fr",
1023
+ -7.226512915547989
1024
+ ],
1025
+ [
1026
+ "▁three",
1027
+ -7.231230878985501
1028
+ ],
1029
+ [
1030
+ "▁used",
1031
+ -7.232260532757048
1032
+ ],
1033
+ [
1034
+ "▁town",
1035
+ -7.232309625465101
1036
+ ],
1037
+ [
1038
+ "came",
1039
+ -7.242967594407505
1040
+ ],
1041
+ [
1042
+ "▁vi",
1043
+ -7.249586832921494
1044
+ ],
1045
+ [
1046
+ "ction",
1047
+ -7.267841526514102
1048
+ ],
1049
+ [
1050
+ "▁high",
1051
+ -7.268061510704944
1052
+ ],
1053
+ [
1054
+ "ous",
1055
+ -7.272224039471849
1056
+ ],
1057
+ [
1058
+ "pp",
1059
+ -7.284848779885527
1060
+ ],
1061
+ [
1062
+ "▁sto",
1063
+ -7.286863027829197
1064
+ ],
1065
+ [
1066
+ "▁however",
1067
+ -7.290660280376883
1068
+ ],
1069
+ [
1070
+ "j",
1071
+ -7.292167342606396
1072
+ ],
1073
+ [
1074
+ "▁fe",
1075
+ -7.29321968286089
1076
+ ],
1077
+ [
1078
+ "land",
1079
+ -7.297367552397095
1080
+ ],
1081
+ [
1082
+ "▁name",
1083
+ -7.2993152341360386
1084
+ ],
1085
+ [
1086
+ "ture",
1087
+ -7.307785305845888
1088
+ ],
1089
+ [
1090
+ "pe",
1091
+ -7.312139567814976
1092
+ ],
1093
+ [
1094
+ "▁ri",
1095
+ -7.323717065692481
1096
+ ],
1097
+ [
1098
+ "▁form",
1099
+ -7.324580994154152
1100
+ ],
1101
+ [
1102
+ "nes",
1103
+ -7.326451748233499
1104
+ ],
1105
+ [
1106
+ "▁ja",
1107
+ -7.328301983192173
1108
+ ],
1109
+ [
1110
+ "ph",
1111
+ -7.337800488161985
1112
+ ],
1113
+ [
1114
+ "▁city",
1115
+ -7.33840895360021
1116
+ ],
1117
+ [
1118
+ "ship",
1119
+ -7.3426208721170045
1120
+ ],
1121
+ [
1122
+ "he",
1123
+ -7.345670806055956
1124
+ ],
1125
+ [
1126
+ "▁va",
1127
+ -7.360810729787437
1128
+ ],
1129
+ [
1130
+ "▁out",
1131
+ -7.363565673300144
1132
+ ],
1133
+ [
1134
+ "▁man",
1135
+ -7.36968256429466
1136
+ ],
1137
+ [
1138
+ "▁state",
1139
+ -7.370327378767264
1140
+ ],
1141
+ [
1142
+ "▁known",
1143
+ -7.370440976732693
1144
+ ],
1145
+ [
1146
+ "port",
1147
+ -7.377756610728268
1148
+ ],
1149
+ [
1150
+ "▁pri",
1151
+ -7.381388302138948
1152
+ ],
1153
+ [
1154
+ "▁gra",
1155
+ -7.383177000548869
1156
+ ],
1157
+ [
1158
+ "ok",
1159
+ -7.383733453838447
1160
+ ],
1161
+ [
1162
+ "▁only",
1163
+ -7.387883335459335
1164
+ ],
1165
+ [
1166
+ "▁col",
1167
+ -7.389262632768462
1168
+ ],
1169
+ [
1170
+ "bo",
1171
+ -7.391109581748884
1172
+ ],
1173
+ [
1174
+ "ical",
1175
+ -7.391580499253513
1176
+ ],
1177
+ [
1178
+ "▁pe",
1179
+ -7.399934877502478
1180
+ ],
1181
+ [
1182
+ "ally",
1183
+ -7.403084708646189
1184
+ ],
1185
+ [
1186
+ "ary",
1187
+ -7.409070412401109
1188
+ ],
1189
+ [
1190
+ "▁over",
1191
+ -7.410534307555428
1192
+ ],
1193
+ [
1194
+ "▁into",
1195
+ -7.410869636527392
1196
+ ],
1197
+ [
1198
+ "ward",
1199
+ -7.419884239492999
1200
+ ],
1201
+ [
1202
+ "▁jo",
1203
+ -7.422160557714333
1204
+ ],
1205
+ [
1206
+ "▁born",
1207
+ -7.430518002046895
1208
+ ],
1209
+ [
1210
+ "▁ga",
1211
+ -7.4335458543965505
1212
+ ],
1213
+ [
1214
+ "▁both",
1215
+ -7.440386115770842
1216
+ ],
1217
+ [
1218
+ "ak",
1219
+ -7.440912383296125
1220
+ ],
1221
+ [
1222
+ "▁wa",
1223
+ -7.444403483510561
1224
+ ],
1225
+ [
1226
+ "▁du",
1227
+ -7.446048536615738
1228
+ ],
1229
+ [
1230
+ "way",
1231
+ -7.450531353727385
1232
+ ],
1233
+ [
1234
+ "ha",
1235
+ -7.451093620092589
1236
+ ],
1237
+ [
1238
+ "min",
1239
+ -7.454793299015211
1240
+ ],
1241
+ [
1242
+ "▁more",
1243
+ -7.46025359771626
1244
+ ],
1245
+ [
1246
+ "▁several",
1247
+ -7.46155351166745
1248
+ ],
1249
+ [
1250
+ "▁may",
1251
+ -7.464386638009014
1252
+ ],
1253
+ [
1254
+ "hi",
1255
+ -7.474873473347444
1256
+ ],
1257
+ [
1258
+ "ach",
1259
+ -7.475967863371558
1260
+ ],
1261
+ [
1262
+ "rie",
1263
+ -7.477430846651114
1264
+ ],
1265
+ [
1266
+ "during",
1267
+ -7.483543807935675
1268
+ ],
1269
+ [
1270
+ "po",
1271
+ -7.488797793905288
1272
+ ],
1273
+ [
1274
+ "to",
1275
+ -7.496399356028629
1276
+ ],
1277
+ [
1278
+ "▁pu",
1279
+ -7.5024247527994845
1280
+ ],
1281
+ [
1282
+ "ition",
1283
+ -7.508572515264678
1284
+ ],
1285
+ [
1286
+ "▁hu",
1287
+ -7.520178891659468
1288
+ ],
1289
+ [
1290
+ "▁call",
1291
+ -7.522546979699779
1292
+ ],
1293
+ [
1294
+ "tro",
1295
+ -7.522743830761915
1296
+ ],
1297
+ [
1298
+ "▁gu",
1299
+ -7.527180358766337
1300
+ ],
1301
+ [
1302
+ "our",
1303
+ -7.527871548238945
1304
+ ],
1305
+ [
1306
+ "▁fo",
1307
+ -7.528734746099595
1308
+ ],
1309
+ [
1310
+ "▁tra",
1311
+ -7.529798113254973
1312
+ ],
1313
+ [
1314
+ "ill",
1315
+ -7.539663319729819
1316
+ ],
1317
+ [
1318
+ "▁war",
1319
+ -7.543107348366025
1320
+ ],
1321
+ [
1322
+ "▁inter",
1323
+ -7.547998188062019
1324
+ ],
1325
+ [
1326
+ "ven",
1327
+ -7.549776682012061
1328
+ ],
1329
+ [
1330
+ "▁through",
1331
+ -7.5509209826877886
1332
+ ],
1333
+ [
1334
+ "▁str",
1335
+ -7.55303390521674
1336
+ ],
1337
+ [
1338
+ "▁area",
1339
+ -7.55309930449728
1340
+ ],
1341
+ [
1342
+ "▁four",
1343
+ -7.5683042519954675
1344
+ ],
1345
+ [
1346
+ "ther",
1347
+ -7.581144427874319
1348
+ ],
1349
+ [
1350
+ "ru",
1351
+ -7.581598878357532
1352
+ ],
1353
+ [
1354
+ "ple",
1355
+ -7.582206344601326
1356
+ ],
1357
+ [
1358
+ "ctor",
1359
+ -7.586640802884986
1360
+ ],
1361
+ [
1362
+ "▁include",
1363
+ -7.591817594156
1364
+ ],
1365
+ [
1366
+ "gan",
1367
+ -7.593009037635843
1368
+ ],
1369
+ [
1370
+ "ial",
1371
+ -7.598363567842016
1372
+ ],
1373
+ [
1374
+ "▁mon",
1375
+ -7.600514066692368
1376
+ ],
1377
+ [
1378
+ "▁found",
1379
+ -7.603177806136431
1380
+ ],
1381
+ [
1382
+ "▁large",
1383
+ -7.60425817554837
1384
+ ],
1385
+ [
1386
+ "▁named",
1387
+ -7.604349942408133
1388
+ ],
1389
+ [
1390
+ "▁film",
1391
+ -7.6107690769879905
1392
+ ],
1393
+ [
1394
+ "one",
1395
+ -7.61168663886918
1396
+ ],
1397
+ [
1398
+ "▁year",
1399
+ -7.613135706422803
1400
+ ],
1401
+ [
1402
+ "cu",
1403
+ -7.61464770866718
1404
+ ],
1405
+ [
1406
+ "▁now",
1407
+ -7.616560120776802
1408
+ ],
1409
+ [
1410
+ "▁main",
1411
+ -7.61875403518334
1412
+ ],
1413
+ [
1414
+ "▁act",
1415
+ -7.619545833972056
1416
+ ],
1417
+ [
1418
+ "▁years",
1419
+ -7.624174493258776
1420
+ ],
1421
+ [
1422
+ "▁under",
1423
+ -7.624641070551563
1424
+ ],
1425
+ [
1426
+ "pla",
1427
+ -7.625342385687491
1428
+ ],
1429
+ [
1430
+ "▁would",
1431
+ -7.62591928350338
1432
+ ],
1433
+ [
1434
+ "▁el",
1435
+ -7.630239688073948
1436
+ ],
1437
+ [
1438
+ "ugh",
1439
+ -7.63104379582024
1440
+ ],
1441
+ [
1442
+ "▁who",
1443
+ -7.637430689406164
1444
+ ],
1445
+ [
1446
+ "▁located",
1447
+ -7.639639663232568
1448
+ ],
1449
+ [
1450
+ "▁ph",
1451
+ -7.641148172672809
1452
+ ],
1453
+ [
1454
+ "qui",
1455
+ -7.650555147784075
1456
+ ],
1457
+ [
1458
+ "▁serve",
1459
+ -7.65118037425113
1460
+ ],
1461
+ [
1462
+ "all",
1463
+ -7.6521999555041855
1464
+ ],
1465
+ [
1466
+ "▁win",
1467
+ -7.657514747870474
1468
+ ],
1469
+ [
1470
+ "out",
1471
+ -7.6620727172990755
1472
+ ],
1473
+ [
1474
+ "▁mu",
1475
+ -7.664262314551301
1476
+ ],
1477
+ [
1478
+ "tra",
1479
+ -7.667073786989784
1480
+ ],
1481
+ [
1482
+ "▁county",
1483
+ -7.678663322169475
1484
+ ],
1485
+ [
1486
+ "ca",
1487
+ -7.678784928209904
1488
+ ],
1489
+ [
1490
+ "▁music",
1491
+ -7.680205798060246
1492
+ ],
1493
+ [
1494
+ "▁member",
1495
+ -7.692517295429374
1496
+ ],
1497
+ [
1498
+ "▁made",
1499
+ -7.692683846728654
1500
+ ],
1501
+ [
1502
+ "▁north",
1503
+ -7.694848927655169
1504
+ ],
1505
+ [
1506
+ "▁ar",
1507
+ -7.695077464636402
1508
+ ],
1509
+ [
1510
+ "▁will",
1511
+ -7.695222090086128
1512
+ ],
1513
+ [
1514
+ "qu",
1515
+ -7.696477395104409
1516
+ ],
1517
+ [
1518
+ "go",
1519
+ -7.699125877208473
1520
+ ],
1521
+ [
1522
+ "▁ju",
1523
+ -7.700622245285146
1524
+ ],
1525
+ [
1526
+ "ative",
1527
+ -7.708442943572338
1528
+ ],
1529
+ [
1530
+ "▁game",
1531
+ -7.714260299934315
1532
+ ],
1533
+ [
1534
+ "▁use",
1535
+ -7.716268759613657
1536
+ ],
1537
+ [
1538
+ "gre",
1539
+ -7.720342078939407
1540
+ ],
1541
+ [
1542
+ "▁south",
1543
+ -7.723597548734455
1544
+ ],
1545
+ [
1546
+ "▁when",
1547
+ -7.724457878007165
1548
+ ],
1549
+ [
1550
+ "gu",
1551
+ -7.725111675361427
1552
+ ],
1553
+ [
1554
+ "ten",
1555
+ -7.728062513332755
1556
+ ],
1557
+ [
1558
+ "▁cu",
1559
+ -7.728757750547128
1560
+ ],
1561
+ [
1562
+ "▁al",
1563
+ -7.731282364559847
1564
+ ],
1565
+ [
1566
+ "▁ru",
1567
+ -7.732636285594861
1568
+ ],
1569
+ [
1570
+ "▁show",
1571
+ -7.734248770118976
1572
+ ],
1573
+ [
1574
+ "▁well",
1575
+ -7.735752980173226
1576
+ ],
1577
+ [
1578
+ "be",
1579
+ -7.73751916529182
1580
+ ],
1581
+ [
1582
+ "que",
1583
+ -7.738416211365767
1584
+ ],
1585
+ [
1586
+ "▁team",
1587
+ -7.744906600273033
1588
+ ],
1589
+ [
1590
+ "▁dec",
1591
+ -7.748590114307557
1592
+ ],
1593
+ [
1594
+ "day",
1595
+ -7.74882057412148
1596
+ ],
1597
+ [
1598
+ "▁live",
1599
+ -7.748841562549558
1600
+ ],
1601
+ [
1602
+ "▁current",
1603
+ -7.749386319744714
1604
+ ],
1605
+ [
1606
+ "▁air",
1607
+ -7.75356733439653
1608
+ ],
1609
+ [
1610
+ "▁song",
1611
+ -7.7575649653318735
1612
+ ],
1613
+ [
1614
+ "▁har",
1615
+ -7.761972061922897
1616
+ ],
1617
+ [
1618
+ "ress",
1619
+ -7.772706521497685
1620
+ ],
1621
+ [
1622
+ "oun",
1623
+ -7.791993882997721
1624
+ ],
1625
+ [
1626
+ "▁end",
1627
+ -7.803556018187734
1628
+ ],
1629
+ [
1630
+ "▁own",
1631
+ -7.810327499800259
1632
+ ],
1633
+ [
1634
+ "▁second",
1635
+ -7.81036139262782
1636
+ ],
1637
+ [
1638
+ "▁long",
1639
+ -7.811157169901499
1640
+ ],
1641
+ [
1642
+ "▁university",
1643
+ -7.812629058127959
1644
+ ],
1645
+ [
1646
+ "▁each",
1647
+ -7.812770346883285
1648
+ ],
1649
+ [
1650
+ "▁people",
1651
+ -7.815571820829902
1652
+ ],
1653
+ [
1654
+ "va",
1655
+ -7.8171224345984704
1656
+ ],
1657
+ [
1658
+ "▁home",
1659
+ -7.818243173720811
1660
+ ],
1661
+ [
1662
+ "▁even",
1663
+ -7.822899150287331
1664
+ ],
1665
+ [
1666
+ "▁near",
1667
+ -7.824766043743408
1668
+ ],
1669
+ [
1670
+ "▁min",
1671
+ -7.833999813522732
1672
+ ],
1673
+ [
1674
+ "▁river",
1675
+ -7.834066727973509
1676
+ ],
1677
+ [
1678
+ "▁album",
1679
+ -7.837144264030833
1680
+ ],
1681
+ [
1682
+ "ner",
1683
+ -7.838310941304613
1684
+ ],
1685
+ [
1686
+ "▁day",
1687
+ -7.838746787913525
1688
+ ],
1689
+ [
1690
+ "▁group",
1691
+ -7.840625948665041
1692
+ ],
1693
+ [
1694
+ "▁tri",
1695
+ -7.845782930179498
1696
+ ],
1697
+ [
1698
+ "▁which",
1699
+ -7.849184674718163
1700
+ ],
1701
+ [
1702
+ "▁very",
1703
+ -7.850118610783806
1704
+ ],
1705
+ [
1706
+ "▁per",
1707
+ -7.852578679917762
1708
+ ],
1709
+ [
1710
+ "▁wi",
1711
+ -7.853345192905438
1712
+ ],
1713
+ [
1714
+ "▁see",
1715
+ -7.854971386721919
1716
+ ],
1717
+ [
1718
+ "▁park",
1719
+ -7.857440569058344
1720
+ ],
1721
+ [
1722
+ "▁remain",
1723
+ -7.866258053049524
1724
+ ],
1725
+ [
1726
+ "▁record",
1727
+ -7.86627372801072
1728
+ ],
1729
+ [
1730
+ "▁plan",
1731
+ -7.867441977404482
1732
+ ],
1733
+ [
1734
+ "▁house",
1735
+ -7.868384538761825
1736
+ ],
1737
+ [
1738
+ "▁cor",
1739
+ -7.8690842103517795
1740
+ ],
1741
+ [
1742
+ "▁cri",
1743
+ -7.869966029419304
1744
+ ],
1745
+ [
1746
+ "ful",
1747
+ -7.872401132052909
1748
+ ],
1749
+ [
1750
+ "▁about",
1751
+ -7.872527635246447
1752
+ ],
1753
+ [
1754
+ "ster",
1755
+ -7.879474628954275
1756
+ ],
1757
+ [
1758
+ "▁hi",
1759
+ -7.8913198820025325
1760
+ ],
1761
+ [
1762
+ "▁ste",
1763
+ -7.891902564264035
1764
+ ],
1765
+ [
1766
+ "▁app",
1767
+ -7.8959806318621535
1768
+ ],
1769
+ [
1770
+ "▁my",
1771
+ -7.902911203934684
1772
+ ],
1773
+ [
1774
+ "▁station",
1775
+ -7.904737946816722
1776
+ ],
1777
+ [
1778
+ "▁trans",
1779
+ -7.905549996358863
1780
+ ],
1781
+ [
1782
+ "▁appear",
1783
+ -7.905789255454087
1784
+ ],
1785
+ [
1786
+ "▁sha",
1787
+ -7.908394538493971
1788
+ ],
1789
+ [
1790
+ "▁fu",
1791
+ -7.909972583185715
1792
+ ],
1793
+ [
1794
+ "▁book",
1795
+ -7.919587941740479
1796
+ ],
1797
+ [
1798
+ "▁number",
1799
+ -7.929104774203541
1800
+ ],
1801
+ [
1802
+ "ron",
1803
+ -7.929257022449795
1804
+ ],
1805
+ [
1806
+ "▁son",
1807
+ -7.931369450893685
1808
+ ],
1809
+ [
1810
+ "▁children",
1811
+ -7.93208047066055
1812
+ ],
1813
+ [
1814
+ "▁bro",
1815
+ -7.933468895640061
1816
+ ],
1817
+ [
1818
+ "▁bra",
1819
+ -7.934700751675502
1820
+ ],
1821
+ [
1822
+ "iv",
1823
+ -7.938760029010922
1824
+ ],
1825
+ [
1826
+ "▁cha",
1827
+ -7.942966567001887
1828
+ ],
1829
+ [
1830
+ "▁did",
1831
+ -7.9447807689970915
1832
+ ],
1833
+ [
1834
+ "▁bar",
1835
+ -7.948634641168312
1836
+ ],
1837
+ [
1838
+ "▁small",
1839
+ -7.951649323586803
1840
+ ],
1841
+ [
1842
+ "▁place",
1843
+ -7.951859486875602
1844
+ ],
1845
+ [
1846
+ "▁family",
1847
+ -7.961935579041397
1848
+ ],
1849
+ [
1850
+ "▁world",
1851
+ -7.966852400342038
1852
+ ],
1853
+ [
1854
+ "▁than",
1855
+ -7.9681738141577565
1856
+ ],
1857
+ [
1858
+ "self",
1859
+ -7.970459138366637
1860
+ ],
1861
+ [
1862
+ "▁take",
1863
+ -7.97161872996911
1864
+ ],
1865
+ [
1866
+ "lie",
1867
+ -7.973214071415059
1868
+ ],
1869
+ [
1870
+ "▁cro",
1871
+ -7.978140550768563
1872
+ ],
1873
+ [
1874
+ "ign",
1875
+ -7.984701206372987
1876
+ ],
1877
+ [
1878
+ "mon",
1879
+ -7.989075509554981
1880
+ ],
1881
+ [
1882
+ "gg",
1883
+ -7.995481614682102
1884
+ ],
1885
+ [
1886
+ "▁je",
1887
+ -7.995540895433944
1888
+ ],
1889
+ [
1890
+ "▁public",
1891
+ -7.998807429280355
1892
+ ],
1893
+ [
1894
+ "▁still",
1895
+ -8.003224829407744
1896
+ ],
1897
+ [
1898
+ "▁what",
1899
+ -8.003618611373797
1900
+ ],
1901
+ [
1902
+ "▁old",
1903
+ -8.005357733122956
1904
+ ],
1905
+ [
1906
+ "▁back",
1907
+ -8.00539355470375
1908
+ ],
1909
+ [
1910
+ "▁local",
1911
+ -8.007126538735287
1912
+ ],
1913
+ [
1914
+ "▁sub",
1915
+ -8.007150555042902
1916
+ ],
1917
+ [
1918
+ "▁char",
1919
+ -8.011578646920904
1920
+ ],
1921
+ [
1922
+ "▁national",
1923
+ -8.012226766921831
1924
+ ],
1925
+ [
1926
+ "field",
1927
+ -8.013402900265072
1928
+ ],
1929
+ [
1930
+ "▁water",
1931
+ -8.013649433342353
1932
+ ],
1933
+ [
1934
+ "▁bri",
1935
+ -8.014045011876082
1936
+ ],
1937
+ [
1938
+ "cent",
1939
+ -8.014160586092588
1940
+ ],
1941
+ [
1942
+ "’",
1943
+ -8.015973953544513
1944
+ ],
1945
+ [
1946
+ "ail",
1947
+ -8.017463589114351
1948
+ ],
1949
+ [
1950
+ "▁like",
1951
+ -8.018145510920542
1952
+ ],
1953
+ [
1954
+ "▁same",
1955
+ -8.026535720563228
1956
+ ],
1957
+ [
1958
+ "▁move",
1959
+ -8.028679732272929
1960
+ ],
1961
+ [
1962
+ "▁often",
1963
+ -8.031925541745231
1964
+ ],
1965
+ [
1966
+ "▁east",
1967
+ -8.032224176872553
1968
+ ],
1969
+ [
1970
+ "▁line",
1971
+ -8.038135161354873
1972
+ ],
1973
+ [
1974
+ "▁village",
1975
+ -8.04567103194289
1976
+ ],
1977
+ [
1978
+ "▁college",
1979
+ -8.046503238925455
1980
+ ],
1981
+ [
1982
+ "▁general",
1983
+ -8.049047221260539
1984
+ ],
1985
+ [
1986
+ "▁release",
1987
+ -8.057666862659708
1988
+ ],
1989
+ [
1990
+ "ual",
1991
+ -8.05941560872936
1992
+ ],
1993
+ [
1994
+ "▁feature",
1995
+ -8.060777601284805
1996
+ ],
1997
+ [
1998
+ "air",
1999
+ -8.06469528557162
2000
+ ],
2001
+ [
2002
+ "bu",
2003
+ -8.06559978520282
2004
+ ],
2005
+ [
2006
+ "▁run",
2007
+ -8.066118548954575
2008
+ ],
2009
+ [
2010
+ "▁life",
2011
+ -8.067827703226232
2012
+ ],
2013
+ [
2014
+ "▁acc",
2015
+ -8.067954466208333
2016
+ ],
2017
+ [
2018
+ "▁tre",
2019
+ -8.070026265483335
2020
+ ],
2021
+ [
2022
+ "produc",
2023
+ -8.076514847803574
2024
+ ],
2025
+ [
2026
+ "▁said",
2027
+ -8.079701979923772
2028
+ ],
2029
+ [
2030
+ "▁service",
2031
+ -8.081143377406775
2032
+ ],
2033
+ [
2034
+ "▁develop",
2035
+ -8.083908661159038
2036
+ ],
2037
+ [
2038
+ "▁original",
2039
+ -8.084503416909131
2040
+ ],
2041
+ [
2042
+ "stan",
2043
+ -8.086469325755983
2044
+ ],
2045
+ [
2046
+ "▁any",
2047
+ -8.098200211461617
2048
+ ],
2049
+ [
2050
+ "▁band",
2051
+ -8.098327335388335
2052
+ ],
2053
+ [
2054
+ "▁perform",
2055
+ -8.098499578240057
2056
+ ],
2057
+ [
2058
+ "▁system",
2059
+ -8.102831580476256
2060
+ ],
2061
+ [
2062
+ "▁district",
2063
+ -8.10761890136164
2064
+ ],
2065
+ [
2066
+ "▁san",
2067
+ -8.108768399104418
2068
+ ],
2069
+ [
2070
+ "▁imp",
2071
+ -8.10929873416065
2072
+ ],
2073
+ [
2074
+ "ities",
2075
+ -8.111638002998978
2076
+ ],
2077
+ [
2078
+ "ches",
2079
+ -8.11285125361874
2080
+ ],
2081
+ [
2082
+ "▁design",
2083
+ -8.116789280836645
2084
+ ],
2085
+ [
2086
+ "▁produce",
2087
+ -8.119375454629434
2088
+ ],
2089
+ [
2090
+ "▁receive",
2091
+ -8.120231190404635
2092
+ ],
2093
+ [
2094
+ "▁building",
2095
+ -8.121898666632525
2096
+ ],
2097
+ [
2098
+ "▁never",
2099
+ -8.126545002135302
2100
+ ],
2101
+ [
2102
+ "ger",
2103
+ -8.130115204245762
2104
+ ],
2105
+ [
2106
+ "▁great",
2107
+ -8.134791142183838
2108
+ ],
2109
+ [
2110
+ "▁young",
2111
+ -8.136855738522952
2112
+ ],
2113
+ [
2114
+ "▁such",
2115
+ -8.138350225328386
2116
+ ],
2117
+ [
2118
+ "wood",
2119
+ -8.13841345163245
2120
+ ],
2121
+ [
2122
+ "ator",
2123
+ -8.140989533059026
2124
+ ],
2125
+ [
2126
+ "▁major",
2127
+ -8.145423610039318
2128
+ ],
2129
+ [
2130
+ "▁down",
2131
+ -8.146806623553081
2132
+ ],
2133
+ [
2134
+ "▁west",
2135
+ -8.147961327620411
2136
+ ],
2137
+ [
2138
+ "cul",
2139
+ -8.157830988907978
2140
+ ],
2141
+ [
2142
+ "ism",
2143
+ -8.158572438822933
2144
+ ],
2145
+ [
2146
+ "▁ten",
2147
+ -8.159322922615742
2148
+ ],
2149
+ [
2150
+ "▁continue",
2151
+ -8.160241541603602
2152
+ ],
2153
+ [
2154
+ "▁open",
2155
+ -8.160628359147328
2156
+ ],
2157
+ [
2158
+ "▁before",
2159
+ -8.161405545705835
2160
+ ],
2161
+ [
2162
+ "▁john",
2163
+ -8.164968593843906
2164
+ ],
2165
+ [
2166
+ "▁mean",
2167
+ -8.168970507760951
2168
+ ],
2169
+ [
2170
+ "▁ki",
2171
+ -8.17127377427151
2172
+ ],
2173
+ [
2174
+ "▁won",
2175
+ -8.173306266378523
2176
+ ],
2177
+ [
2178
+ "cause",
2179
+ -8.175055296509452
2180
+ ],
2181
+ [
2182
+ "▁common",
2183
+ -8.176677746872262
2184
+ ],
2185
+ [
2186
+ "▁list",
2187
+ -8.178624124918302
2188
+ ],
2189
+ [
2190
+ "▁church",
2191
+ -8.179415838121052
2192
+ ],
2193
+ [
2194
+ "▁term",
2195
+ -8.182013213445382
2196
+ ],
2197
+ [
2198
+ "▁different",
2199
+ -8.184204788104076
2200
+ ],
2201
+ [
2202
+ "▁consider",
2203
+ -8.1851563338407
2204
+ ],
2205
+ [
2206
+ "▁five",
2207
+ -8.196664391335384
2208
+ ],
2209
+ [
2210
+ "▁company",
2211
+ -8.196896682724828
2212
+ ],
2213
+ [
2214
+ "▁lead",
2215
+ -8.200721273934157
2216
+ ],
2217
+ [
2218
+ "▁return",
2219
+ -8.203718862552664
2220
+ ],
2221
+ [
2222
+ "▁following",
2223
+ -8.207902699370319
2224
+ ],
2225
+ [
2226
+ "▁married",
2227
+ -8.209051623603013
2228
+ ],
2229
+ [
2230
+ "▁bre",
2231
+ -8.210483287529804
2232
+ ],
2233
+ [
2234
+ "▁between",
2235
+ -8.210691903680361
2236
+ ],
2237
+ [
2238
+ "▁tu",
2239
+ -8.213462772326872
2240
+ ],
2241
+ [
2242
+ "▁rec",
2243
+ -8.215463926545171
2244
+ ],
2245
+ [
2246
+ "▁gen",
2247
+ -8.215917728114515
2248
+ ],
2249
+ [
2250
+ "ham",
2251
+ -8.216969035771678
2252
+ ],
2253
+ [
2254
+ "▁short",
2255
+ -8.217254141523233
2256
+ ],
2257
+ [
2258
+ "oli",
2259
+ -8.225614503442134
2260
+ ],
2261
+ [
2262
+ "▁father",
2263
+ -8.22848236716985
2264
+ ],
2265
+ [
2266
+ "▁law",
2267
+ -8.228647185217952
2268
+ ],
2269
+ [
2270
+ "▁arm",
2271
+ -8.229279277171369
2272
+ ],
2273
+ [
2274
+ "▁six",
2275
+ -8.231654543783572
2276
+ ],
2277
+ [
2278
+ "▁stand",
2279
+ -8.232833790933514
2280
+ ],
2281
+ [
2282
+ "▁island",
2283
+ -8.23295114550086
2284
+ ],
2285
+ [
2286
+ "▁office",
2287
+ -8.238200655391111
2288
+ ],
2289
+ [
2290
+ "▁while",
2291
+ -8.244641901510835
2292
+ ],
2293
+ [
2294
+ "less",
2295
+ -8.248924390600386
2296
+ ],
2297
+ [
2298
+ "▁disc",
2299
+ -8.256617994514315
2300
+ ],
2301
+ [
2302
+ "nish",
2303
+ -8.259199372621973
2304
+ ],
2305
+ [
2306
+ "gra",
2307
+ -8.260633621736485
2308
+ ],
2309
+ [
2310
+ "▁black",
2311
+ -8.260770647781088
2312
+ ],
2313
+ [
2314
+ "▁white",
2315
+ -8.261792308266608
2316
+ ],
2317
+ [
2318
+ "▁dra",
2319
+ -8.262200199231897
2320
+ ],
2321
+ [
2322
+ "ney",
2323
+ -8.263411110832958
2324
+ ],
2325
+ [
2326
+ "▁sk",
2327
+ -8.265500405965897
2328
+ ],
2329
+ [
2330
+ "▁another",
2331
+ -8.265674793319524
2332
+ ],
2333
+ [
2334
+ "▁series",
2335
+ -8.266294741377507
2336
+ ],
2337
+ [
2338
+ "▁club",
2339
+ -8.267002341514132
2340
+ ],
2341
+ [
2342
+ "▁last",
2343
+ -8.269236209393974
2344
+ ],
2345
+ [
2346
+ "▁just",
2347
+ -8.273349054761749
2348
+ ],
2349
+ [
2350
+ "▁every",
2351
+ -8.278006948910186
2352
+ ],
2353
+ [
2354
+ "com",
2355
+ -8.280018321637833
2356
+ ],
2357
+ [
2358
+ "▁season",
2359
+ -8.288115490272684
2360
+ ],
2361
+ [
2362
+ "▁port",
2363
+ -8.290733597489803
2364
+ ],
2365
+ [
2366
+ "▁where",
2367
+ -8.295184730987494
2368
+ ],
2369
+ [
2370
+ "▁qua",
2371
+ -8.296429350369845
2372
+ ],
2373
+ [
2374
+ "▁give",
2375
+ -8.299217726872731
2376
+ ],
2377
+ [
2378
+ "▁change",
2379
+ -8.308720458584265
2380
+ ],
2381
+ [
2382
+ "▁make",
2383
+ -8.313624648627616
2384
+ ],
2385
+ [
2386
+ "▁success",
2387
+ -8.313757975103245
2388
+ ],
2389
+ [
2390
+ "▁head",
2391
+ -8.31419639704875
2392
+ ],
2393
+ [
2394
+ "val",
2395
+ -8.315678259685662
2396
+ ],
2397
+ [
2398
+ "▁creat",
2399
+ -8.31584048827423
2400
+ ],
2401
+ [
2402
+ "▁support",
2403
+ -8.321849696327526
2404
+ ],
2405
+ [
2406
+ "▁could",
2407
+ -8.322515152783604
2408
+ ],
2409
+ [
2410
+ "▁seat",
2411
+ -8.32640134292371
2412
+ ],
2413
+ [
2414
+ "▁train",
2415
+ -8.330865992183835
2416
+ ],
2417
+ [
2418
+ "▁road",
2419
+ -8.331399184562759
2420
+ ],
2421
+ [
2422
+ "▁point",
2423
+ -8.334421095707848
2424
+ ],
2425
+ [
2426
+ "▁result",
2427
+ -8.336023620788348
2428
+ ],
2429
+ [
2430
+ "▁class",
2431
+ -8.340924837616088
2432
+ ],
2433
+ [
2434
+ "▁united",
2435
+ -8.348404927787627
2436
+ ],
2437
+ [
2438
+ "▁attend",
2439
+ -8.360275666972496
2440
+ ],
2441
+ [
2442
+ "▁provide",
2443
+ -8.363626658034661
2444
+ ],
2445
+ [
2446
+ "▁left",
2447
+ -8.366263886762164
2448
+ ],
2449
+ [
2450
+ "▁region",
2451
+ -8.368167962944623
2452
+ ],
2453
+ [
2454
+ "▁much",
2455
+ -8.368402208046183
2456
+ ],
2457
+ [
2458
+ "▁since",
2459
+ -8.368429053605361
2460
+ ],
2461
+ [
2462
+ "▁program",
2463
+ -8.374836424335937
2464
+ ],
2465
+ [
2466
+ "▁side",
2467
+ -8.376583200926818
2468
+ ],
2469
+ [
2470
+ "▁york",
2471
+ -8.380279040621806
2472
+ ],
2473
+ [
2474
+ "▁close",
2475
+ -8.380373085198691
2476
+ ],
2477
+ [
2478
+ "▁community",
2479
+ -8.390043406624867
2480
+ ],
2481
+ [
2482
+ "▁lake",
2483
+ -8.392204961484412
2484
+ ],
2485
+ [
2486
+ "���hand",
2487
+ -8.396433663089894
2488
+ ],
2489
+ [
2490
+ "mission",
2491
+ -8.401877281679974
2492
+ ],
2493
+ [
2494
+ "▁saint",
2495
+ -8.402298456733927
2496
+ ],
2497
+ [
2498
+ "▁brother",
2499
+ -8.404312226238739
2500
+ ],
2501
+ [
2502
+ "▁early",
2503
+ -8.407057265507136
2504
+ ],
2505
+ [
2506
+ "ug",
2507
+ -8.419115623966269
2508
+ ],
2509
+ [
2510
+ "▁single",
2511
+ -8.421887011591389
2512
+ ],
2513
+ [
2514
+ "▁popular",
2515
+ -8.423581002353854
2516
+ ],
2517
+ [
2518
+ "▁ka",
2519
+ -8.425682083968539
2520
+ ],
2521
+ [
2522
+ "▁government",
2523
+ -8.431993278395476
2524
+ ],
2525
+ [
2526
+ "▁refer",
2527
+ -8.432759908155642
2528
+ ],
2529
+ [
2530
+ "▁good",
2531
+ -8.434851815345286
2532
+ ],
2533
+ [
2534
+ "ized",
2535
+ -8.436194795790644
2536
+ ],
2537
+ [
2538
+ "ground",
2539
+ -8.438060934245975
2540
+ ],
2541
+ [
2542
+ "nder",
2543
+ -8.44084331443392
2544
+ ],
2545
+ [
2546
+ "▁final",
2547
+ -8.441099307688706
2548
+ ],
2549
+ [
2550
+ "▁german",
2551
+ -8.446351868468698
2552
+ ],
2553
+ [
2554
+ "▁publish",
2555
+ -8.44811269015751
2556
+ ],
2557
+ [
2558
+ "▁cover",
2559
+ -8.450661822121575
2560
+ ],
2561
+ [
2562
+ "▁around",
2563
+ -8.45801269553424
2564
+ ],
2565
+ [
2566
+ "▁tru",
2567
+ -8.465945416864763
2568
+ ],
2569
+ [
2570
+ "▁free",
2571
+ -8.466937917450903
2572
+ ],
2573
+ [
2574
+ "▁death",
2575
+ -8.471387109509486
2576
+ ],
2577
+ [
2578
+ "▁character",
2579
+ -8.47925380341218
2580
+ ],
2581
+ [
2582
+ "▁cra",
2583
+ -8.480388755035024
2584
+ ],
2585
+ [
2586
+ "▁street",
2587
+ -8.481857857041343
2588
+ ],
2589
+ [
2590
+ "▁career",
2591
+ -8.485696642742031
2592
+ ],
2593
+ [
2594
+ "▁follow",
2595
+ -8.487054795889959
2596
+ ],
2597
+ [
2598
+ "▁little",
2599
+ -8.493929657535503
2600
+ ],
2601
+ [
2602
+ "▁daughter",
2603
+ -8.495838031310194
2604
+ ],
2605
+ [
2606
+ "▁right",
2607
+ -8.49938327486857
2608
+ ],
2609
+ [
2610
+ "▁blo",
2611
+ -8.504736151694356
2612
+ ],
2613
+ [
2614
+ "▁studie",
2615
+ -8.507158028275926
2616
+ ],
2617
+ [
2618
+ "▁title",
2619
+ -8.507564681345778
2620
+ ],
2621
+ [
2622
+ "▁power",
2623
+ -8.511276797327884
2624
+ ],
2625
+ [
2626
+ "▁held",
2627
+ -8.515310155299764
2628
+ ],
2629
+ [
2630
+ "ford",
2631
+ -8.515923299326781
2632
+ ],
2633
+ [
2634
+ "▁student",
2635
+ -8.517949142703806
2636
+ ],
2637
+ [
2638
+ "▁site",
2639
+ -8.521783262108439
2640
+ ],
2641
+ [
2642
+ "▁language",
2643
+ -8.526534303494756
2644
+ ],
2645
+ [
2646
+ "▁sign",
2647
+ -8.530535229851592
2648
+ ],
2649
+ [
2650
+ "▁person",
2651
+ -8.532003665866414
2652
+ ],
2653
+ [
2654
+ "▁dan",
2655
+ -8.534603981452662
2656
+ ],
2657
+ [
2658
+ "▁next",
2659
+ -8.536724744790396
2660
+ ],
2661
+ [
2662
+ "▁contain",
2663
+ -8.53724021736098
2664
+ ],
2665
+ [
2666
+ "▁written",
2667
+ -8.537538191946581
2668
+ ],
2669
+ [
2670
+ "▁built",
2671
+ -8.537564784011852
2672
+ ],
2673
+ [
2674
+ "▁english",
2675
+ -8.541233022321085
2676
+ ],
2677
+ [
2678
+ "▁manag",
2679
+ -8.541411310908908
2680
+ ],
2681
+ [
2682
+ "▁again",
2683
+ -8.543463036773398
2684
+ ],
2685
+ [
2686
+ "▁track",
2687
+ -8.549096848636776
2688
+ ],
2689
+ [
2690
+ "▁become",
2691
+ -8.5505817092827
2692
+ ],
2693
+ [
2694
+ "▁addition",
2695
+ -8.563724537950346
2696
+ ],
2697
+ [
2698
+ "ified",
2699
+ -8.563753973454977
2700
+ ],
2701
+ [
2702
+ "▁usual",
2703
+ -8.566681752436955
2704
+ ],
2705
+ [
2706
+ "▁get",
2707
+ -8.567392155490447
2708
+ ],
2709
+ [
2710
+ "▁availabl",
2711
+ -8.571643418051458
2712
+ ],
2713
+ [
2714
+ "▁center",
2715
+ -8.574426393488245
2716
+ ],
2717
+ [
2718
+ "uff",
2719
+ -8.574573366537244
2720
+ ],
2721
+ [
2722
+ "▁present",
2723
+ -8.580592559305742
2724
+ ],
2725
+ [
2726
+ "▁along",
2727
+ -8.58128059442477
2728
+ ],
2729
+ [
2730
+ "▁council",
2731
+ -8.589140398796983
2732
+ ],
2733
+ [
2734
+ "▁turn",
2735
+ -8.592979495777078
2736
+ ],
2737
+ [
2738
+ "▁green",
2739
+ -8.598366406527138
2740
+ ],
2741
+ [
2742
+ "▁count",
2743
+ -8.601811261637131
2744
+ ],
2745
+ [
2746
+ "▁mother",
2747
+ -8.60917887040323
2748
+ ],
2749
+ [
2750
+ "spect",
2751
+ -8.616966412856792
2752
+ ],
2753
+ [
2754
+ "▁look",
2755
+ -8.623242916827012
2756
+ ],
2757
+ [
2758
+ "▁london",
2759
+ -8.623263516450116
2760
+ ],
2761
+ [
2762
+ "ville",
2763
+ -8.625035670776107
2764
+ ],
2765
+ [
2766
+ "▁represent",
2767
+ -8.625449075298462
2768
+ ],
2769
+ [
2770
+ "▁history",
2771
+ -8.625869986710171
2772
+ ],
2773
+ [
2774
+ "▁version",
2775
+ -8.631353483577167
2776
+ ],
2777
+ [
2778
+ "▁international",
2779
+ -8.634276172051226
2780
+ ],
2781
+ [
2782
+ "▁court",
2783
+ -8.634998422314329
2784
+ ],
2785
+ [
2786
+ "▁various",
2787
+ -8.635383508148188
2788
+ ],
2789
+ [
2790
+ "▁president",
2791
+ -8.636493086624457
2792
+ ],
2793
+ [
2794
+ "▁business",
2795
+ -8.636863367535444
2796
+ ],
2797
+ [
2798
+ "▁among",
2799
+ -8.64000108582483
2800
+ ],
2801
+ [
2802
+ "▁flow",
2803
+ -8.640479428725959
2804
+ ],
2805
+ [
2806
+ "▁light",
2807
+ -8.641530059379548
2808
+ ],
2809
+ [
2810
+ "▁help",
2811
+ -8.647441596103139
2812
+ ],
2813
+ [
2814
+ "▁order",
2815
+ -8.64861737687781
2816
+ ],
2817
+ [
2818
+ "▁hill",
2819
+ -8.65204824091686
2820
+ ],
2821
+ [
2822
+ "▁complete",
2823
+ -8.660665816625905
2824
+ ],
2825
+ [
2826
+ "▁similar",
2827
+ -8.66731645121796
2828
+ ],
2829
+ [
2830
+ "▁week",
2831
+ -8.669176248324836
2832
+ ],
2833
+ [
2834
+ "▁word",
2835
+ -8.669623600409947
2836
+ ],
2837
+ [
2838
+ "▁offer",
2839
+ -8.675409935441808
2840
+ ],
2841
+ [
2842
+ "▁important",
2843
+ -8.679221405674415
2844
+ ],
2845
+ [
2846
+ "▁wife",
2847
+ -8.680119542779103
2848
+ ],
2849
+ [
2850
+ "▁third",
2851
+ -8.680798513458852
2852
+ ],
2853
+ [
2854
+ "▁europe",
2855
+ -8.68425651958696
2856
+ ],
2857
+ [
2858
+ "▁football",
2859
+ -8.694794948303976
2860
+ ],
2861
+ [
2862
+ "▁know",
2863
+ -8.70808700609502
2864
+ ],
2865
+ [
2866
+ "▁period",
2867
+ -8.708236352219206
2868
+ ],
2869
+ [
2870
+ "▁woman",
2871
+ -8.70912189579257
2872
+ ],
2873
+ [
2874
+ "▁species",
2875
+ -8.712212355389836
2876
+ ],
2877
+ [
2878
+ "▁blue",
2879
+ -8.713037621854472
2880
+ ],
2881
+ [
2882
+ "▁enter",
2883
+ -8.713052698133598
2884
+ ],
2885
+ [
2886
+ "against",
2887
+ -8.714412797815836
2888
+ ],
2889
+ [
2890
+ "▁settle",
2891
+ -8.715915482394756
2892
+ ],
2893
+ [
2894
+ "▁operate",
2895
+ -8.717045325823666
2896
+ ],
2897
+ [
2898
+ "▁author",
2899
+ -8.717423149151815
2900
+ ],
2901
+ [
2902
+ "▁exist",
2903
+ -8.7253180719574
2904
+ ],
2905
+ [
2906
+ "▁eight",
2907
+ -8.728034899341813
2908
+ ],
2909
+ [
2910
+ "▁project",
2911
+ -8.729937576855761
2912
+ ],
2913
+ [
2914
+ "▁sometimes",
2915
+ -8.734008547807601
2916
+ ],
2917
+ [
2918
+ "▁special",
2919
+ -8.741374050821644
2920
+ ],
2921
+ [
2922
+ "▁child",
2923
+ -8.747484726940964
2924
+ ],
2925
+ [
2926
+ "▁example",
2927
+ -8.747572909454611
2928
+ ],
2929
+ [
2930
+ "▁league",
2931
+ -8.752544235031802
2932
+ ],
2933
+ [
2934
+ "▁type",
2935
+ -8.755095330832773
2936
+ ],
2937
+ [
2938
+ "▁engine",
2939
+ -8.759635996925297
2940
+ ],
2941
+ [
2942
+ "▁collect",
2943
+ -8.759859172926044
2944
+ ],
2945
+ [
2946
+ "▁grow",
2947
+ -8.762688448938803
2948
+ ],
2949
+ [
2950
+ "▁surviv",
2951
+ -8.763835496149287
2952
+ ],
2953
+ [
2954
+ "▁though",
2955
+ -8.765961027715528
2956
+ ],
2957
+ [
2958
+ "▁level",
2959
+ -8.772041953413918
2960
+ ],
2961
+ [
2962
+ "▁british",
2963
+ -8.781646781141653
2964
+ ],
2965
+ [
2966
+ "burg",
2967
+ -8.782109628693906
2968
+ ],
2969
+ [
2970
+ "▁fish",
2971
+ -8.785727132173403
2972
+ ],
2973
+ [
2974
+ "▁eventual",
2975
+ -8.78599819623117
2976
+ ],
2977
+ [
2978
+ "▁walk",
2979
+ -8.786273773044563
2980
+ ],
2981
+ [
2982
+ "▁farm",
2983
+ -8.787884660123996
2984
+ ],
2985
+ [
2986
+ "▁friend",
2987
+ -8.791545567410537
2988
+ ],
2989
+ [
2990
+ "▁girl",
2991
+ -8.792859715640407
2992
+ ],
2993
+ [
2994
+ "▁describe",
2995
+ -8.794135213475116
2996
+ ],
2997
+ [
2998
+ "▁grand",
2999
+ -8.797914720177122
3000
+ ],
3001
+ [
3002
+ "▁pra",
3003
+ -8.801743694975219
3004
+ ],
3005
+ [
3006
+ "▁french",
3007
+ -8.804636753869945
3008
+ ],
3009
+ [
3010
+ "▁mountain",
3011
+ -8.810740380898126
3012
+ ],
3013
+ [
3014
+ "▁william",
3015
+ -8.81213443408776
3016
+ ],
3017
+ [
3018
+ "▁central",
3019
+ -8.812514204231366
3020
+ ],
3021
+ [
3022
+ "▁those",
3023
+ -8.815268051810754
3024
+ ],
3025
+ [
3026
+ "▁historic",
3027
+ -8.817124151070487
3028
+ ],
3029
+ [
3030
+ "▁should",
3031
+ -8.822263968962837
3032
+ ],
3033
+ [
3034
+ "bility",
3035
+ -8.825843476855038
3036
+ ],
3037
+ [
3038
+ "▁construct",
3039
+ -8.82718187472506
3040
+ ],
3041
+ [
3042
+ "ency",
3043
+ -8.83150706603628
3044
+ ],
3045
+ [
3046
+ "▁wrot",
3047
+ -8.837571561595198
3048
+ ],
3049
+ [
3050
+ "▁consist",
3051
+ -8.842652643641848
3052
+ ],
3053
+ [
3054
+ "▁australia",
3055
+ -8.846626741298131
3056
+ ],
3057
+ [
3058
+ "▁effect",
3059
+ -8.847997803512609
3060
+ ],
3061
+ [
3062
+ "▁process",
3063
+ -8.84901200095267
3064
+ ],
3065
+ [
3066
+ "▁replac",
3067
+ -8.849360841452432
3068
+ ],
3069
+ [
3070
+ "▁control",
3071
+ -8.852403434628375
3072
+ ],
3073
+ [
3074
+ "ology",
3075
+ -8.852877971924125
3076
+ ],
3077
+ [
3078
+ "▁england",
3079
+ -8.854427120471016
3080
+ ],
3081
+ [
3082
+ "▁includ",
3083
+ -8.85878984229386
3084
+ ],
3085
+ [
3086
+ "���write",
3087
+ -8.860317339202346
3088
+ ],
3089
+ [
3090
+ "▁further",
3091
+ -8.86090855209244
3092
+ ],
3093
+ [
3094
+ "▁position",
3095
+ -8.866286184735717
3096
+ ],
3097
+ [
3098
+ "▁women",
3099
+ -8.86696169453236
3100
+ ],
3101
+ [
3102
+ "▁together",
3103
+ -8.869799173981853
3104
+ ],
3105
+ [
3106
+ "▁video",
3107
+ -8.887124180111755
3108
+ ],
3109
+ [
3110
+ "▁occur",
3111
+ -8.888124747828993
3112
+ ],
3113
+ [
3114
+ "▁previous",
3115
+ -8.896255937560948
3116
+ ],
3117
+ [
3118
+ "▁involve",
3119
+ -8.89721391467737
3120
+ ],
3121
+ [
3122
+ "▁require",
3123
+ -8.898803593163606
3124
+ ],
3125
+ [
3126
+ "▁issue",
3127
+ -8.902682904684076
3128
+ ],
3129
+ [
3130
+ "▁model",
3131
+ -8.903230207757918
3132
+ ],
3133
+ [
3134
+ "▁centre",
3135
+ -8.912180621179559
3136
+ ],
3137
+ [
3138
+ "▁official",
3139
+ -8.912705660016188
3140
+ ],
3141
+ [
3142
+ "▁education",
3143
+ -8.922018097144344
3144
+ ],
3145
+ [
3146
+ "▁subsequent",
3147
+ -8.922510440111688
3148
+ ],
3149
+ [
3150
+ "▁cemetery",
3151
+ -8.931419209988611
3152
+ ],
3153
+ [
3154
+ "▁director",
3155
+ -8.935937539574503
3156
+ ],
3157
+ [
3158
+ "▁battle",
3159
+ -8.947502148354001
3160
+ ],
3161
+ [
3162
+ "▁museum",
3163
+ -8.951512658304399
3164
+ ],
3165
+ [
3166
+ "▁northern",
3167
+ -8.951916463250939
3168
+ ],
3169
+ [
3170
+ "▁artist",
3171
+ -8.953811567205221
3172
+ ],
3173
+ [
3174
+ "▁research",
3175
+ -8.964268273840068
3176
+ ],
3177
+ [
3178
+ "▁strong",
3179
+ -8.965970223651727
3180
+ ],
3181
+ [
3182
+ "▁market",
3183
+ -8.968622701662255
3184
+ ],
3185
+ [
3186
+ "▁political",
3187
+ -8.973039284330682
3188
+ ],
3189
+ [
3190
+ "▁problem",
3191
+ -8.973559619952457
3192
+ ],
3193
+ [
3194
+ "▁review",
3195
+ -8.975638997595691
3196
+ ],
3197
+ [
3198
+ "▁sound",
3199
+ -8.975977122352809
3200
+ ],
3201
+ [
3202
+ "▁style",
3203
+ -8.976176394221653
3204
+ ],
3205
+ [
3206
+ "▁leave",
3207
+ -8.977548989088348
3208
+ ],
3209
+ [
3210
+ "▁california",
3211
+ -8.980843398409057
3212
+ ],
3213
+ [
3214
+ "▁attack",
3215
+ -8.982962739927693
3216
+ ],
3217
+ [
3218
+ "▁range",
3219
+ -8.985729838044836
3220
+ ],
3221
+ [
3222
+ "▁organiz",
3223
+ -8.988726922831367
3224
+ ],
3225
+ [
3226
+ "▁brown",
3227
+ -8.998720503761433
3228
+ ],
3229
+ [
3230
+ "▁western",
3231
+ -8.999643026933589
3232
+ ],
3233
+ [
3234
+ "▁novel",
3235
+ -9.000218912912711
3236
+ ],
3237
+ [
3238
+ "▁modern",
3239
+ -9.001985996102455
3240
+ ],
3241
+ [
3242
+ "▁independen",
3243
+ -9.003025460321094
3244
+ ],
3245
+ [
3246
+ "▁champion",
3247
+ -9.003031332715086
3248
+ ],
3249
+ [
3250
+ "▁round",
3251
+ -9.01089257525527
3252
+ ],
3253
+ [
3254
+ "▁always",
3255
+ -9.014031753493049
3256
+ ],
3257
+ [
3258
+ "until",
3259
+ -9.017485978405505
3260
+ ],
3261
+ [
3262
+ "▁limit",
3263
+ -9.017747642672813
3264
+ ],
3265
+ [
3266
+ "▁capital",
3267
+ -9.025208555516956
3268
+ ],
3269
+ [
3270
+ "▁nav",
3271
+ -9.036214093417485
3272
+ ],
3273
+ [
3274
+ "stead",
3275
+ -9.038761616772518
3276
+ ],
3277
+ [
3278
+ "▁sister",
3279
+ -9.041954428574062
3280
+ ],
3281
+ [
3282
+ "▁bridge",
3283
+ -9.043474718270652
3284
+ ],
3285
+ [
3286
+ "hood",
3287
+ -9.053521622777172
3288
+ ],
3289
+ [
3290
+ "▁source",
3291
+ -9.062504658078463
3292
+ ],
3293
+ [
3294
+ "▁middle",
3295
+ -9.070992453580974
3296
+ ],
3297
+ [
3298
+ "▁entire",
3299
+ -9.077889166105958
3300
+ ],
3301
+ [
3302
+ "▁origin",
3303
+ -9.08432968742058
3304
+ ],
3305
+ [
3306
+ "▁private",
3307
+ -9.088282545245027
3308
+ ],
3309
+ [
3310
+ "▁railway",
3311
+ -9.09176405323294
3312
+ ],
3313
+ [
3314
+ "script",
3315
+ -9.095365653342965
3316
+ ],
3317
+ [
3318
+ "▁establish",
3319
+ -9.097614929235975
3320
+ ],
3321
+ [
3322
+ "▁course",
3323
+ -9.098861308440863
3324
+ ],
3325
+ [
3326
+ "▁military",
3327
+ -9.099377861676238
3328
+ ],
3329
+ [
3330
+ "▁method",
3331
+ -9.114198214049043
3332
+ ],
3333
+ [
3334
+ "▁television",
3335
+ -9.117176904131602
3336
+ ],
3337
+ [
3338
+ "▁social",
3339
+ -9.117818473849477
3340
+ ],
3341
+ [
3342
+ "▁civil",
3343
+ -9.11898023552438
3344
+ ],
3345
+ [
3346
+ "▁border",
3347
+ -9.123240593057512
3348
+ ],
3349
+ [
3350
+ "▁travel",
3351
+ -9.135767295622834
3352
+ ],
3353
+ [
3354
+ "▁africa",
3355
+ -9.137135089263122
3356
+ ],
3357
+ [
3358
+ "▁numerous",
3359
+ -9.140187327155555
3360
+ ],
3361
+ [
3362
+ "ograph",
3363
+ -9.141979637162184
3364
+ ],
3365
+ [
3366
+ "▁canada",
3367
+ -9.14829270959714
3368
+ ],
3369
+ [
3370
+ "▁typical",
3371
+ -9.151275066866766
3372
+ ],
3373
+ [
3374
+ "▁resident",
3375
+ -9.153758592596224
3376
+ ],
3377
+ [
3378
+ "embl",
3379
+ -9.156516831069087
3380
+ ],
3381
+ [
3382
+ "▁practice",
3383
+ -9.161235920546735
3384
+ ],
3385
+ [
3386
+ "▁separate",
3387
+ -9.161865477490087
3388
+ ],
3389
+ [
3390
+ "▁drive",
3391
+ -9.164561808409092
3392
+ ],
3393
+ [
3394
+ "▁episode",
3395
+ -9.168139434816258
3396
+ ],
3397
+ [
3398
+ "▁surround",
3399
+ -9.17192615052093
3400
+ ],
3401
+ [
3402
+ "▁structure",
3403
+ -9.177633273927295
3404
+ ],
3405
+ [
3406
+ "▁particular",
3407
+ -9.17763354042183
3408
+ ],
3409
+ [
3410
+ "▁believe",
3411
+ -9.180274459538897
3412
+ ],
3413
+ [
3414
+ "▁george",
3415
+ -9.18337981163793
3416
+ ],
3417
+ [
3418
+ "▁almost",
3419
+ -9.188504152905503
3420
+ ],
3421
+ [
3422
+ "▁primary",
3423
+ -9.205397585951523
3424
+ ],
3425
+ [
3426
+ "▁oppos",
3427
+ -9.207991380266536
3428
+ ],
3429
+ [
3430
+ "▁parish",
3431
+ -9.20929604698349
3432
+ ],
3433
+ [
3434
+ "▁valley",
3435
+ -9.211974501351284
3436
+ ],
3437
+ [
3438
+ "▁radio",
3439
+ -9.21382264807512
3440
+ ],
3441
+ [
3442
+ "▁municipal",
3443
+ -9.220510803902828
3444
+ ],
3445
+ [
3446
+ "▁population",
3447
+ -9.220510979344862
3448
+ ],
3449
+ [
3450
+ "▁natural",
3451
+ -9.241981256185802
3452
+ ],
3453
+ [
3454
+ "▁commercial",
3455
+ -9.244697406730166
3456
+ ],
3457
+ [
3458
+ "▁influence",
3459
+ -9.25495085346992
3460
+ ],
3461
+ [
3462
+ "▁across",
3463
+ -9.256326284814747
3464
+ ],
3465
+ [
3466
+ "▁increase",
3467
+ -9.256327258400416
3468
+ ],
3469
+ [
3470
+ "▁regular",
3471
+ -9.25770439125096
3472
+ ],
3473
+ [
3474
+ "▁facilit",
3475
+ -9.259084648852792
3476
+ ],
3477
+ [
3478
+ "▁america",
3479
+ -9.263962803540426
3480
+ ],
3481
+ [
3482
+ "▁hospital",
3483
+ -9.269483647188489
3484
+ ],
3485
+ [
3486
+ "▁chief",
3487
+ -9.27440782920186
3488
+ ],
3489
+ [
3490
+ "▁significant",
3491
+ -9.275777252665556
3492
+ ],
3493
+ [
3494
+ "▁department",
3495
+ -9.277884028156835
3496
+ ],
3497
+ [
3498
+ "▁elected",
3499
+ -9.27858792830147
3500
+ ],
3501
+ [
3502
+ "▁industry",
3503
+ -9.287774883201791
3504
+ ],
3505
+ [
3506
+ "▁information",
3507
+ -9.288484870034107
3508
+ ],
3509
+ [
3510
+ "▁occasion",
3511
+ -9.292756790528593
3512
+ ],
3513
+ [
3514
+ "▁possibl",
3515
+ -9.293471685050614
3516
+ ],
3517
+ [
3518
+ "▁voice",
3519
+ -9.294308454586137
3520
+ ],
3521
+ [
3522
+ "▁russia",
3523
+ -9.294524578818091
3524
+ ],
3525
+ [
3526
+ "▁frequent",
3527
+ -9.296331052513468
3528
+ ],
3529
+ [
3530
+ "▁writing",
3531
+ -9.30280302036764
3532
+ ],
3533
+ [
3534
+ "▁society",
3535
+ -9.306406437689832
3536
+ ],
3537
+ [
3538
+ "▁appoint",
3539
+ -9.307138209700025
3540
+ ],
3541
+ [
3542
+ "▁employ",
3543
+ -9.307854252148935
3544
+ ],
3545
+ [
3546
+ "▁subject",
3547
+ -9.31658466568389
3548
+ ],
3549
+ [
3550
+ "▁contribut",
3551
+ -9.317316164023172
3552
+ ],
3553
+ [
3554
+ "▁attempt",
3555
+ -9.326130278902296
3556
+ ],
3557
+ [
3558
+ "▁festival",
3559
+ -9.33875041448835
3560
+ ],
3561
+ [
3562
+ "▁headquarter",
3563
+ -9.340994140116074
3564
+ ],
3565
+ [
3566
+ "▁magazine",
3567
+ -9.34174318900008
3568
+ ],
3569
+ [
3570
+ "▁introduc",
3571
+ -9.347003718055843
3572
+ ],
3573
+ [
3574
+ "▁select",
3575
+ -9.347576876301837
3576
+ ],
3577
+ [
3578
+ "▁protect",
3579
+ -9.35080352014047
3580
+ ],
3581
+ [
3582
+ "▁republic",
3583
+ -9.35836616238581
3584
+ ],
3585
+ [
3586
+ "▁individual",
3587
+ -9.362948072222718
3588
+ ],
3589
+ [
3590
+ "▁except",
3591
+ -9.364534105456542
3592
+ ],
3593
+ [
3594
+ "▁studio",
3595
+ -9.3667824469869
3596
+ ],
3597
+ [
3598
+ "▁david",
3599
+ -9.367555460558028
3600
+ ],
3601
+ [
3602
+ "▁study",
3603
+ -9.37449627486125
3604
+ ],
3605
+ [
3606
+ "”",
3607
+ -9.379152128763874
3608
+ ],
3609
+ [
3610
+ "▁yellow",
3611
+ -9.385398534472024
3612
+ ],
3613
+ [
3614
+ "▁professional",
3615
+ -9.390102570312028
3616
+ ],
3617
+ [
3618
+ "▁christian",
3619
+ -9.39167678588908
3620
+ ],
3621
+ [
3622
+ "“",
3623
+ -9.39720599339324
3624
+ ],
3625
+ [
3626
+ "▁competition",
3627
+ -9.399590054766064
3628
+ ],
3629
+ [
3630
+ "▁architect",
3631
+ -9.401969807983903
3632
+ ],
3633
+ [
3634
+ "▁associate",
3635
+ -9.40595717077596
3636
+ ],
3637
+ [
3638
+ "▁network",
3639
+ -9.413174416029864
3640
+ ],
3641
+ [
3642
+ "▁platform",
3643
+ -9.418824128957128
3644
+ ],
3645
+ [
3646
+ "▁province",
3647
+ -9.41882530778206
3648
+ ],
3649
+ [
3650
+ "▁educate",
3651
+ -9.4285931028375
3652
+ ],
3653
+ [
3654
+ "▁succeed",
3655
+ -9.43268361268196
3656
+ ],
3657
+ [
3658
+ "▁experience",
3659
+ -9.438440784217477
3660
+ ],
3661
+ [
3662
+ "▁object",
3663
+ -9.445066983476966
3664
+ ],
3665
+ [
3666
+ "▁association",
3667
+ -9.44672910556617
3668
+ ],
3669
+ [
3670
+ "▁difficult",
3671
+ -9.455926485547485
3672
+ ],
3673
+ [
3674
+ "▁immediate",
3675
+ -9.458449618275022
3676
+ ],
3677
+ [
3678
+ "▁journal",
3679
+ -9.462670239021836
3680
+ ],
3681
+ [
3682
+ "▁observ",
3683
+ -9.48492694663403
3684
+ ],
3685
+ [
3686
+ "▁academy",
3687
+ -9.490103247109989
3688
+ ],
3689
+ [
3690
+ "▁committee",
3691
+ -9.51118439539725
3692
+ ],
3693
+ [
3694
+ "▁specific",
3695
+ -9.512072499477846
3696
+ ],
3697
+ [
3698
+ "▁newspaper",
3699
+ -9.516524937949235
3700
+ ],
3701
+ [
3702
+ "▁catholic",
3703
+ -9.5201015950536
3704
+ ],
3705
+ [
3706
+ "▁certain",
3707
+ -9.523690778511131
3708
+ ],
3709
+ [
3710
+ "incorporate",
3711
+ -9.551951131559653
3712
+ ],
3713
+ [
3714
+ "▁economic",
3715
+ -9.553801898702435
3716
+ ],
3717
+ [
3718
+ "‘",
3719
+ -9.57155936963102
3720
+ ],
3721
+ [
3722
+ "▁instrument",
3723
+ -9.574392626922052
3724
+ ],
3725
+ [
3726
+ "▁parliament",
3727
+ -9.582939295715178
3728
+ ],
3729
+ [
3730
+ "▁distinct",
3731
+ -9.58775500128628
3732
+ ],
3733
+ [
3734
+ "▁unknown",
3735
+ -9.589637899752152
3736
+ ],
3737
+ [
3738
+ "▁distribut",
3739
+ -9.59348595392874
3740
+ ],
3741
+ [
3742
+ "▁manufactur",
3743
+ -9.611968904963938
3744
+ ],
3745
+ [
3746
+ "specially",
3747
+ -9.619871974666424
3748
+ ],
3749
+ [
3750
+ "▁michael",
3751
+ -9.63883651220214
3752
+ ],
3753
+ [
3754
+ "▁democrat",
3755
+ -9.639845273542909
3756
+ ],
3757
+ [
3758
+ "▁affect",
3759
+ -9.682130226089695
3760
+ ],
3761
+ [
3762
+ "▁broadcast",
3763
+ -9.691643496522142
3764
+ ],
3765
+ [
3766
+ "▁electric",
3767
+ -9.703408357083504
3768
+ ],
3769
+ [
3770
+ "▁railroad",
3771
+ -9.71858476735134
3772
+ ],
3773
+ [
3774
+ "▁institute",
3775
+ -9.738442109092423
3776
+ ],
3777
+ [
3778
+ "▁virginia",
3779
+ -9.7782199841132
3780
+ ],
3781
+ [
3782
+ "▁executive",
3783
+ -9.778219992852405
3784
+ ],
3785
+ [
3786
+ "▁nickname",
3787
+ -9.788709584330268
3788
+ ],
3789
+ [
3790
+ "▁principal",
3791
+ -9.796944922609374
3792
+ ],
3793
+ [
3794
+ "▁technique",
3795
+ -9.83670919121584
3796
+ ],
3797
+ [
3798
+ "▁environment",
3799
+ -9.865389459222612
3800
+ ],
3801
+ [
3802
+ "q",
3803
+ -9.876882881751468
3804
+ ],
3805
+ [
3806
+ "▁basketball",
3807
+ -9.888423102346794
3808
+ ],
3809
+ [
3810
+ "▁recogniz",
3811
+ -9.913326174623208
3812
+ ],
3813
+ [
3814
+ "▁investigat",
3815
+ -9.934789091309357
3816
+ ],
3817
+ [
3818
+ "▁administrative",
3819
+ -10.088374855936404
3820
+ ],
3821
+ [
3822
+ "—",
3823
+ -10.109142371045758
3824
+ ],
3825
+ [
3826
+ "▁pennsylvania",
3827
+ -10.136967400536996
3828
+ ],
3829
+ [
3830
+ "▁metropolitan",
3831
+ -10.141959090291545
3832
+ ],
3833
+ [
3834
+ "▁massachusetts",
3835
+ -10.170725872445
3836
+ ],
3837
+ [
3838
+ "é",
3839
+ -11.174417433920302
3840
+ ],
3841
+ [
3842
+ "–",
3843
+ -11.453548440521548
3844
+ ],
3845
+ [
3846
+ "ü",
3847
+ -11.524090256941632
3848
+ ],
3849
+ [
3850
+ "ä",
3851
+ -12.089533105118232
3852
+ ],
3853
+ [
3854
+ "ö",
3855
+ -12.296719802233156
3856
+ ],
3857
+ [
3858
+ "á",
3859
+ -12.435400432633775
3860
+ ],
3861
+ [
3862
+ "í",
3863
+ -12.577226894888064
3864
+ ],
3865
+ [
3866
+ "ó",
3867
+ -12.742544952256411
3868
+ ],
3869
+ [
3870
+ "ç",
3871
+ -13.120283714665124
3872
+ ],
3873
+ [
3874
+ "â",
3875
+ -13.339312667832004
3876
+ ],
3877
+ [
3878
+ "ß",
3879
+ -13.339312667832004
3880
+ ],
3881
+ [
3882
+ "à",
3883
+ -13.380979334498672
3884
+ ],
3885
+ [
3886
+ "ō",
3887
+ -13.734541852356523
3888
+ ],
3889
+ [
3890
+ "ú",
3891
+ -13.79704185235653
3892
+ ],
3893
+ [
3894
+ "ô",
3895
+ -14.095393500708347
3896
+ ],
3897
+ [
3898
+ "ï",
3899
+ -14.18630259161771
3900
+ ],
3901
+ [
3902
+ "ł",
3903
+ -14.522413702741172
3904
+ ],
3905
+ [
3906
+ "ã",
3907
+ -14.522413702741174
3908
+ ],
3909
+ [
3910
+ "…",
3911
+ -14.522413702741174
3912
+ ],
3913
+ [
3914
+ "ë",
3915
+ -14.665270845598318
3916
+ ],
3917
+ [
3918
+ "ć",
3919
+ -14.831937512264984
3920
+ ],
3921
+ [
3922
+ "ø",
3923
+ -14.831937512304942
3924
+ ],
3925
+ [
3926
+ "č",
3927
+ -14.831937512304943
3928
+ ],
3929
+ [
3930
+ "ă",
3931
+ -15.031937512304935
3932
+ ],
3933
+ [
3934
+ "´",
3935
+ -15.281937512264983
3936
+ ],
3937
+ [
3938
+ "š",
3939
+ -15.281937512264989
3940
+ ],
3941
+ [
3942
+ "î",
3943
+ -15.281937512304944
3944
+ ],
3945
+ [
3946
+ "û",
3947
+ -15.61527084559832
3948
+ ],
3949
+ [
3950
+ "ž",
3951
+ -15.615270845598324
3952
+ ],
3953
+ [
3954
+ "ș",
3955
+ -15.615270845638266
3956
+ ],
3957
+ [
3958
+ "ò",
3959
+ -15.615270845638276
3960
+ ],
3961
+ [
3962
+ "ā",
3963
+ -15.615270845638276
3964
+ ],
3965
+ [
3966
+ "]",
3967
+ -15.615270845638276
3968
+ ],
3969
+ [
3970
+ "ř",
3971
+ -16.115270845598324
3972
+ ],
3973
+ [
3974
+ "ş",
3975
+ -16.11527084563828
3976
+ ],
3977
+ [
3978
+ "ı",
3979
+ -16.11527084563828
3980
+ ],
3981
+ [
3982
+ "α",
3983
+ -16.11527084563828
3984
+ ],
3985
+ [
3986
+ "å",
3987
+ -16.11527084563828
3988
+ ],
3989
+ [
3990
+ "»",
3991
+ -16.11527084563828
3992
+ ],
3993
+ [
3994
+ "ʻ",
3995
+ -16.11527084563828
3996
+ ],
3997
+ [
3998
+ "π",
3999
+ -17.114470845638277
4000
+ ],
4001
+ [
4002
+ "œ",
4003
+ -17.11457084563828
4004
+ ],
4005
+ [
4006
+ "«",
4007
+ -17.11467084563828
4008
+ ],
4009
+ [
4010
+ "·",
4011
+ -17.11477084563828
4012
+ ],
4013
+ [
4014
+ "ū",
4015
+ -17.11487084563828
4016
+ ],
4017
+ [
4018
+ "è",
4019
+ -17.11497084563828
4020
+ ],
4021
+ [
4022
+ "[",
4023
+ -17.11507084563828
4024
+ ],
4025
+ [
4026
+ "ê",
4027
+ -17.11517084563828
4028
+ ],
4029
+ [
4030
+ "ạ",
4031
+ -17.115270845598324
4032
+ ],
4033
+ [
4034
+ "ī",
4035
+ -17.115270845638264
4036
+ ],
4037
+ [
4038
+ "阪",
4039
+ -17.11527084563828
4040
+ ],
4041
+ [
4042
+ "京",
4043
+ -17.11527084563828
4044
+ ],
4045
+ [
4046
+ "→",
4047
+ -17.11527084563828
4048
+ ],
4049
+ [
4050
+ "χ",
4051
+ -17.11527084563828
4052
+ ],
4053
+ [
4054
+ "ע",
4055
+ -17.11527084563828
4056
+ ],
4057
+ [
4058
+ "ị",
4059
+ -17.11527084563828
4060
+ ],
4061
+ [
4062
+ "ð",
4063
+ -17.11527084563828
4064
+ ],
4065
+ [
4066
+ "熊",
4067
+ -17.11527084563828
4068
+ ],
4069
+ [
4070
+ "а",
4071
+ -17.11527084563828
4072
+ ],
4073
+ [
4074
+ "ñ",
4075
+ -17.11527084563828
4076
+ ],
4077
+ [
4078
+ "ả",
4079
+ -17.11527084563828
4080
+ ],
4081
+ [
4082
+ "ő",
4083
+ -17.11527084563828
4084
+ ],
4085
+ [
4086
+ "大",
4087
+ -17.11527084563828
4088
+ ],
4089
+ [
4090
+ "时",
4091
+ -17.11527084563828
4092
+ ],
4093
+ [
4094
+ "ń",
4095
+ -17.11527084563828
4096
+ ],
4097
+ [
4098
+ "ý",
4099
+ -17.11527084563828
4100
+ ],
4101
+ [
4102
+ "尚",
4103
+ -17.11527084563828
4104
+ ],
4105
+ [
4106
+ "先",
4107
+ -17.11527084563828
4108
+ ],
4109
+ [
4110
+ "€",
4111
+ -17.11527084563828
4112
+ ],
4113
+ [
4114
+ "„",
4115
+ -17.11527084563828
4116
+ ],
4117
+ [
4118
+ "奔",
4119
+ -17.11527084563828
4120
+ ],
4121
+ [
4122
+ "生",
4123
+ -17.11527084563828
4124
+ ],
4125
+ [
4126
+ "¡",
4127
+ -17.11527084563828
4128
+ ],
4129
+ [
4130
+ "都",
4131
+ -17.11527084563828
4132
+ ],
4133
+ [
4134
+ "נ",
4135
+ -17.11527084563828
4136
+ ],
4137
+ [
4138
+ "ň",
4139
+ -17.11527084563828
4140
+ ]
4141
+ ],
4142
+ "byte_fallback": false
4143
+ }
4144
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "([bos])",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "([eos])",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "([unk])",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "([pad])",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "([mask])",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "8": {
44
+ "content": "▁",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "([bos])",
53
+ "clean_up_tokenization_spaces": true,
54
+ "eos_token": "([eos])",
55
+ "mask_token": "([mask])",
56
+ "model_max_length": 1000000000000000019884624838656,
57
+ "pad_token": "([pad])",
58
+ "sep_token": "▁",
59
+ "tokenizer_class": "PreTrainedTokenizerFast",
60
+ "unk_token": "([unk])"
61
+ }