MBMMurad commited on
Commit
adaa392
1 Parent(s): 368a8e5

Upload new lm-boosted decoder

Browse files
.gitattributes CHANGED
@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zst filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zst filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
32
+ language_model/unigrams.txt filter=lfs diff=lfs merge=lfs -text
alphabet.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"labels": [" ", "!", "'", ",", "-", ".", ":", ";", "=", "?", "\u0964", "\u0981", "\u0982", "\u0983", "\u0985", "\u0986", "\u0987", "\u0988", "\u0989", "\u098a", "\u098b", "\u098f", "\u0990", "\u0993", "\u0994", "\u0995", "\u0996", "\u0997", "\u0998", "\u0999", "\u099a", "\u099b", "\u099c", "\u099d", "\u099e", "\u099f", "\u09a0", "\u09a1", "\u09a2", "\u09a3", "\u09a4", "\u09a5", "\u09a6", "\u09a7", "\u09a8", "\u09aa", "\u09ab", "\u09ac", "\u09ad", "\u09ae", "\u09af", "\u09b0", "\u09b2", "\u09b6", "\u09b7", "\u09b8", "\u09b9", "\u09be", "\u09bf", "\u09c0", "\u09c1", "\u09c2", "\u09c3", "\u09c7", "\u09c8", "\u09cb", "\u09cc", "\u09cd", "\u09ce", "\u09dc", "\u09dd", "\u09df", "\u09e6", "\u09e7", "\u09e8", "\u09e9", "\u09ea", "\u09eb", "\u09ec", "\u09ed", "\u09ee", "\u09ef", "\u200d", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
language_model/6gram.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:854863b2d7ef86d1dab687cbd0894c4ab048358de11058e3e9c2f47b5fca6170
3
+ size 8319130332
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f80a16e5bcddb0b96faa8311173b9595b5dcb6c87e9d8bcc139fe0ef88cc89c8
3
+ size 106370349
preprocessor_config.json CHANGED
@@ -4,6 +4,7 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
 
7
  "return_attention_mask": true,
8
  "sampling_rate": 16000
9
  }
 
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2ProcessorWithLM",
8
  "return_attention_mask": true,
9
  "sampling_rate": 16000
10
  }
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
@@ -2,8 +2,9 @@
2
  "bos_token": "<s>",
3
  "do_lower_case": false,
4
  "eos_token": "</s>",
5
- "name_or_path": "./",
6
  "pad_token": "[PAD]",
 
7
  "replace_word_delimiter_char": " ",
8
  "special_tokens_map_file": null,
9
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
2
  "bos_token": "<s>",
3
  "do_lower_case": false,
4
  "eos_token": "</s>",
5
+ "name_or_path": "MBMMurad/wav2vec2_murad_with_some_new_data",
6
  "pad_token": "[PAD]",
7
+ "processor_class": "Wav2Vec2ProcessorWithLM",
8
  "replace_word_delimiter_char": " ",
9
  "special_tokens_map_file": null,
10
  "tokenizer_class": "Wav2Vec2CTCTokenizer",