lsb commited on
Commit
3e1c71b
1 Parent(s): 66874a0

Upload lm-boosted decoder

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ language_model/5gram_correct.arpa filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 26, "</s>": 27}
alphabet.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"labels": [" ", "a", "b", "c", "d", "e", "f", "g", "h", "i", "k", "l", "m", "n", "o", "p", "q", "r", "s", "t", "u", "x", "y", "z", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
language_model/5gram_correct.arpa ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c55ee2a1bd82e29398688fffb0a73e3b1543b00ca6edc7226a67d6416376690
3
+ size 428318639
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 CHANGED
@@ -4,6 +4,7 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
 
7
  "return_attention_mask": false,
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": false,
9
  "sampling_rate": 16000
10
  }
special_tokens_map.json CHANGED
@@ -1 +1 @@
1
- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": "/root/.cache/huggingface/transformers/50cab4efe4eb39b04aaa98cbbbb08065883e251e762f577c9bdcf88ac9e6cc1b.a21d51735cf8667bcd610f057e88548d5d6a381401f6b4501a8bc6c1a9dc8498", "tokenizer_file": null, "name_or_path": "lsb/wav2vec2-base-pemlsb-la", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}