gary109 commited on
Commit
0e37304
1 Parent(s): 03e4d58

Upload lm-boosted decoder

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 17,
3
+ "<s>": 16
4
+ }
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 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ a1.
13
+ a2
14
+ a2.
15
+ a3
16
+ a3.
17
+ a4
18
+ a4.
19
+ a5
20
+ b2
21
+ b2.
22
+ b3
23
+ b3.
24
+ b4
25
+ b4.
26
+ b5
27
+ c#3
28
+ c#3.
29
+ c#4
30
+ c#4.
31
+ c#5
32
+ c#5.
33
+ c3
34
+ c3.
35
+ c4
36
+ c4.
37
+ c5
38
+ c5.
39
+ d#3
40
+ d#3.
41
+ d#4
42
+ d#4.
43
+ d#5
44
+ d#5.
45
+ d2
46
+ d3
47
+ d3.
48
+ d4
49
+ d4.
50
+ d5
51
+ d5.
52
+ e2
53
+ e2.
54
+ e3
55
+ e3.
56
+ e4
57
+ e4.
58
+ e5
59
+ e5.
60
+ f#2
61
+ f#2.
62
+ f#3
63
+ f#3.
64
+ f#4
65
+ f#4.
66
+ f#5
67
+ f#5.
68
+ f1
69
+ f2
70
+ f3
71
+ f3.
72
+ f4
73
+ f4.
74
+ f5
75
+ f5.
76
+ g#2
77
+ g#2.
78
+ g#3
79
+ g#3.
80
+ g#4
81
+ g#4.
82
+ g#5
83
+ g#5.
84
+ g2
85
+ g2.
86
+ g3
87
+ g3.
88
+ g4
89
+ g4.
90
+ g5
91
+ g5.
special_tokens_map.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<s>",
33
+ "lstrip": false,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "</s>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<s>",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "</s>",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<s>",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "</s>",
68
+ "lstrip": false,
69
+ "normalized": true,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ }
73
+ ],
74
+ "bos_token": "<s>",
75
+ "eos_token": "</s>",
76
+ "pad_token": "[PAD]",
77
+ "unk_token": "[UNK]"
78
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "name_or_path": "gary109/ai-light-dance_singing_ft_wav2vec2-large-xlsr-53-5gram",
6
+ "pad_token": "[PAD]",
7
+ "processor_class": "Wav2Vec2ProcessorWithLM",
8
+ "replace_word_delimiter_char": " ",
9
+ "special_tokens_map_file": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "trust_remote_code": false,
12
+ "unk_token": "[UNK]",
13
+ "word_delimiter_token": "|"
14
+ }
vocab.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "#": 1,
3
+ "1": 2,
4
+ "2": 3,
5
+ "3": 4,
6
+ "4": 5,
7
+ "5": 6,
8
+ "[PAD]": 15,
9
+ "[UNK]": 14,
10
+ "a": 7,
11
+ "b": 8,
12
+ "c": 9,
13
+ "d": 10,
14
+ "e": 11,
15
+ "f": 12,
16
+ "g": 13,
17
+ "|": 0
18
+ }