pongjin commited on
Commit
c2d3f98
·
1 Parent(s): 598d386

Upload w2v2_lm

Browse files
language_model/5gram.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db082c7e12cd5daae6375e0189c52b746482ff08afef4160097747d82dc28ff4
3
+ size 1839642621
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
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,5 +1,19 @@
1
  {
2
  "additional_special_tokens": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  {
4
  "content": "<s>",
5
  "lstrip": false,
 
1
  {
2
  "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
  {
18
  "content": "<s>",
19
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -8,6 +8,7 @@
8
  "replace_word_delimiter_char": " ",
9
  "special_tokens_map_file": "/root/.cache/huggingface/transformers/8f068c6d948c1719d32f70f7634619826c4baf71fe02ec6d099b3f39536b8d73.fea372b8528a479b7415f13ca4e27a2f5f3782cbb3f15b4d19bb3cbe734e8137",
10
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
11
  "unk_token": "[UNK]",
12
  "word_delimiter_token": "|"
13
  }
 
8
  "replace_word_delimiter_char": " ",
9
  "special_tokens_map_file": "/root/.cache/huggingface/transformers/8f068c6d948c1719d32f70f7634619826c4baf71fe02ec6d099b3f39536b8d73.fea372b8528a479b7415f13ca4e27a2f5f3782cbb3f15b4d19bb3cbe734e8137",
10
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "trust_remote_code": false,
12
  "unk_token": "[UNK]",
13
  "word_delimiter_token": "|"
14
  }