gary109 commited on
Commit
c8a4dda
1 Parent(s): 5b21eb6

Upload lm-boosted decoder new

Browse files
alphabet.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"labels": [" ", "#", "1", "2", "3", "4", "5", "a", "b", "c", "d", "e", "f", "g", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
language_model/5gram_correct.arpa ADDED
The diff for this file is too large to render. See raw diff
 
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 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ </s>
2
+ <s>
3
+ a#2
4
+ a#2.
5
+ a#3
6
+ a#3.
7
+ a#4
8
+ a#4.
9
+ a#5
10
+ a#5.
11
+ a1
12
+ a2
13
+ a2.
14
+ a3
15
+ a3.
16
+ a4
17
+ a4.
18
+ a5
19
+ b2
20
+ b2.
21
+ b3
22
+ b3.
23
+ b4
24
+ b4.
25
+ b5
26
+ c#3
27
+ c#3.
28
+ c#4
29
+ c#4.
30
+ c#5
31
+ c#5.
32
+ c3
33
+ c3.
34
+ c4
35
+ c4.
36
+ c5
37
+ c5.
38
+ d#3
39
+ d#3.
40
+ d#4
41
+ d#4.
42
+ d#5
43
+ d#5.
44
+ d2
45
+ d3
46
+ d3.
47
+ d4
48
+ d4.
49
+ d5
50
+ d5.
51
+ e2
52
+ e2.
53
+ e3
54
+ e3.
55
+ e4
56
+ e4.
57
+ e5
58
+ e5.
59
+ f#2
60
+ f#2.
61
+ f#3
62
+ f#3.
63
+ f#4
64
+ f#4.
65
+ f#5
66
+ f#5.
67
+ f1
68
+ f2
69
+ f3
70
+ f3.
71
+ f4
72
+ f4.
73
+ f5
74
+ f5.
75
+ g#2
76
+ g#2.
77
+ g#3
78
+ g#3.
79
+ g#4
80
+ g#4.
81
+ g#5
82
+ g#5.
83
+ g2
84
+ g2.
85
+ g3
86
+ g3.
87
+ g4
88
+ g4.
89
+ g5
preprocessor_config.json CHANGED
@@ -4,6 +4,7 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0,
 
7
  "return_attention_mask": true,
8
  "sampling_rate": 16000
9
  }
 
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0,
7
+ "processor_class": "Wav2Vec2ProcessorWithLM",
8
  "return_attention_mask": true,
9
  "sampling_rate": 16000
10
  }
special_tokens_map.json CHANGED
@@ -245,6 +245,20 @@
245
  "rstrip": false,
246
  "single_word": false
247
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
248
  {
249
  "content": "</s>",
250
  "lstrip": false,
 
245
  "rstrip": false,
246
  "single_word": false
247
  },
248
+ {
249
+ "content": "</s>",
250
+ "lstrip": false,
251
+ "normalized": true,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ },
255
+ {
256
+ "content": "<s>",
257
+ "lstrip": false,
258
+ "normalized": true,
259
+ "rstrip": false,
260
+ "single_word": false
261
+ },
262
  {
263
  "content": "</s>",
264
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -2,9 +2,9 @@
2
  "bos_token": "<s>",
3
  "do_lower_case": false,
4
  "eos_token": "</s>",
5
- "name_or_path": "ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1",
6
  "pad_token": "[PAD]",
7
- "processor_class": "Wav2Vec2Processor",
8
  "replace_word_delimiter_char": " ",
9
  "special_tokens_map_file": null,
10
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
2
  "bos_token": "<s>",
3
  "do_lower_case": false,
4
  "eos_token": "</s>",
5
+ "name_or_path": "gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1",
6
  "pad_token": "[PAD]",
7
+ "processor_class": "Wav2Vec2ProcessorWithLM",
8
  "replace_word_delimiter_char": " ",
9
  "special_tokens_map_file": null,
10
  "tokenizer_class": "Wav2Vec2CTCTokenizer",