yip-i commited on
Commit
bd08c7b
1 Parent(s): 1f82124

Upload lm-boosted decoder

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 31,
3
+ "<s>": 30
4
+ }
alphabet.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"labels": ["b", "q", "g", " ", "o", "s", "m", "d", "z", "a", "c", "w", "j", "f", "t", "k", "y", "n", "'", "l", "p", "x", "u", "h", "e", "v", "r", "i", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
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
 
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
@@ -1,4 +1,20 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "<s>",
3
  "eos_token": "</s>",
4
  "pad_token": "[PAD]",
 
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
  "bos_token": "<s>",
19
  "eos_token": "</s>",
20
  "pad_token": "[PAD]",
tokenizer_config.json CHANGED
@@ -3,8 +3,11 @@
3
  "do_lower_case": false,
4
  "eos_token": "</s>",
5
  "model_max_length": 1000000000000000019884624838656,
 
6
  "pad_token": "[PAD]",
 
7
  "replace_word_delimiter_char": " ",
 
8
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
9
  "unk_token": "[UNK]",
10
  "word_delimiter_token": "|"
 
3
  "do_lower_case": false,
4
  "eos_token": "</s>",
5
  "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "yip-i/torgo_xlsr_finetune-F03-2",
7
  "pad_token": "[PAD]",
8
+ "processor_class": "Wav2Vec2ProcessorWithLM",
9
  "replace_word_delimiter_char": " ",
10
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--yip-i--torgo_xlsr_finetune-F03-2/snapshots/1f821248784c556b7d8423ae6130589c9adf9160/special_tokens_map.json",
11
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
12
  "unk_token": "[UNK]",
13
  "word_delimiter_token": "|"