language_model
Browse files- alphabet.json +1 -0
- language_model/5gram_correct.arpa +0 -0
- language_model/attrs.json +1 -0
- language_model/unigrams.txt +77 -0
- special_tokens_map.json +106 -0
- tokenizer_config.json +14 -0
- vocab.json +18 -0
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 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
a3
|
14 |
+
a3.
|
15 |
+
a4
|
16 |
+
a4.
|
17 |
+
a5
|
18 |
+
b2
|
19 |
+
b3
|
20 |
+
b3.
|
21 |
+
b4
|
22 |
+
b4.
|
23 |
+
b5
|
24 |
+
c#3
|
25 |
+
c#3.
|
26 |
+
c#4
|
27 |
+
c#4.
|
28 |
+
c#5
|
29 |
+
c#5.
|
30 |
+
c3
|
31 |
+
c4
|
32 |
+
c4.
|
33 |
+
c5
|
34 |
+
c5.
|
35 |
+
d#3
|
36 |
+
d#3.
|
37 |
+
d#4
|
38 |
+
d#4.
|
39 |
+
d#5
|
40 |
+
d2
|
41 |
+
d3
|
42 |
+
d3.
|
43 |
+
d4
|
44 |
+
d4.
|
45 |
+
d5
|
46 |
+
d5.
|
47 |
+
e2
|
48 |
+
e3
|
49 |
+
e3.
|
50 |
+
e4
|
51 |
+
e4.
|
52 |
+
e5
|
53 |
+
f#2
|
54 |
+
f#3
|
55 |
+
f#3.
|
56 |
+
f#4
|
57 |
+
f#4.
|
58 |
+
f#5
|
59 |
+
f1
|
60 |
+
f2
|
61 |
+
f3
|
62 |
+
f3.
|
63 |
+
f4
|
64 |
+
f4.
|
65 |
+
f5
|
66 |
+
g#2
|
67 |
+
g#3
|
68 |
+
g#3.
|
69 |
+
g#4
|
70 |
+
g#4.
|
71 |
+
g#5
|
72 |
+
g2
|
73 |
+
g3
|
74 |
+
g3.
|
75 |
+
g4
|
76 |
+
g4.
|
77 |
+
g5
|
special_tokens_map.json
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"content": "<s>",
|
75 |
+
"lstrip": false,
|
76 |
+
"normalized": true,
|
77 |
+
"rstrip": false,
|
78 |
+
"single_word": false
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"content": "</s>",
|
82 |
+
"lstrip": false,
|
83 |
+
"normalized": true,
|
84 |
+
"rstrip": false,
|
85 |
+
"single_word": false
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"content": "<s>",
|
89 |
+
"lstrip": false,
|
90 |
+
"normalized": true,
|
91 |
+
"rstrip": false,
|
92 |
+
"single_word": false
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"content": "</s>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": true,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false
|
100 |
+
}
|
101 |
+
],
|
102 |
+
"bos_token": "<s>",
|
103 |
+
"eos_token": "</s>",
|
104 |
+
"pad_token": "[PAD]",
|
105 |
+
"unk_token": "[UNK]"
|
106 |
+
}
|
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_singing2_ft_wav2vec2-large-xlsr-53-5gram-v4-1",
|
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 |
+
}
|