Kuray107 commited on
Commit
2fecc80
·
1 Parent(s): 3f4e47b

Upload 4-gram lsLM-boosted decoder

Browse files
.gitattributes CHANGED
@@ -26,3 +26,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
26
  *.zip filter=lfs diff=lfs merge=lfs -text
27
  *.zstandard filter=lfs diff=lfs merge=lfs -text
28
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
26
  *.zip filter=lfs diff=lfs merge=lfs -text
27
  *.zstandard filter=lfs diff=lfs merge=lfs -text
28
  *tfevents* filter=lfs diff=lfs merge=lfs -text
29
+ language_model/4-gram.arpa filter=lfs diff=lfs merge=lfs -text
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/4-gram.arpa ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb250ea20b0673a2ae48f9c069094f4974641cc6554befffce0711bd9d8ffed2
3
+ size 4395628122
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
 
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "return_attention_mask": false, "do_normalize": true, "special_tokens_map_file": "/nethome/pku9/.cache/huggingface/transformers/ea87275f5fc43818a621a24808e31620120aed1ea33894682213553a8b7c34ac.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd", "tokenizer_file": null, "name_or_path": "facebook/wav2vec2-large-960h", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "E": 5, "T": 6, "A": 7, "O": 8, "N": 9, "I": 10, "H": 11, "S": 12, "R": 13, "D": 14, "L": 15, "U": 16, "M": 17, "W": 18, "C": 19, "F": 20, "G": 21, "Y": 22, "P": 23, "B": 24, "V": 25, "K": 26, "'": 27, "X": 28, "J": 29, "Q": 30, "Z": 31}