sahinbatmaz
commited on
Commit
•
b04d738
1
Parent(s):
a3f4402
Upload processor
Browse files- added_tokens.json +4 -0
- preprocessor_config.json +10 -0
- special_tokens_map.json +36 -0
- tokenizer_config.json +14 -0
- vocab.json +117 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 38,
|
3 |
+
"<s>": 37
|
4 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
+
"return_attention_mask": true,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"bos_token": "<s>",
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"pad_token": "[PAD]",
|
35 |
+
"unk_token": "[UNK]"
|
36 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"processor_class": "Wav2Vec2Processor",
|
9 |
+
"replace_word_delimiter_char": " ",
|
10 |
+
"target_lang": "tur",
|
11 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
12 |
+
"unk_token": "[UNK]",
|
13 |
+
"word_delimiter_token": "|"
|
14 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"swe": {
|
3 |
+
"!": 56,
|
4 |
+
"\"": 30,
|
5 |
+
"$": 70,
|
6 |
+
"%": 55,
|
7 |
+
"&": 60,
|
8 |
+
"'": 51,
|
9 |
+
"+": 58,
|
10 |
+
",": 47,
|
11 |
+
"-": 33,
|
12 |
+
".": 34,
|
13 |
+
"/": 50,
|
14 |
+
"0": 31,
|
15 |
+
"1": 32,
|
16 |
+
"2": 36,
|
17 |
+
"3": 41,
|
18 |
+
"4": 40,
|
19 |
+
"5": 39,
|
20 |
+
"6": 43,
|
21 |
+
"7": 45,
|
22 |
+
"8": 44,
|
23 |
+
"9": 38,
|
24 |
+
":": 46,
|
25 |
+
";": 53,
|
26 |
+
"</s>": 2,
|
27 |
+
"<s>": 1,
|
28 |
+
"?": 72,
|
29 |
+
"[": 67,
|
30 |
+
"[PAD]": 0,
|
31 |
+
"[UNK]": 3,
|
32 |
+
"]": 68,
|
33 |
+
"a": 6,
|
34 |
+
"b": 26,
|
35 |
+
"c": 27,
|
36 |
+
"d": 13,
|
37 |
+
"e": 5,
|
38 |
+
"f": 19,
|
39 |
+
"g": 17,
|
40 |
+
"h": 23,
|
41 |
+
"i": 11,
|
42 |
+
"j": 29,
|
43 |
+
"k": 16,
|
44 |
+
"l": 12,
|
45 |
+
"m": 15,
|
46 |
+
"n": 9,
|
47 |
+
"o": 14,
|
48 |
+
"p": 21,
|
49 |
+
"q": 48,
|
50 |
+
"r": 7,
|
51 |
+
"s": 10,
|
52 |
+
"t": 8,
|
53 |
+
"u": 22,
|
54 |
+
"v": 18,
|
55 |
+
"w": 37,
|
56 |
+
"x": 35,
|
57 |
+
"y": 28,
|
58 |
+
"z": 42,
|
59 |
+
"|": 4,
|
60 |
+
"°": 63,
|
61 |
+
"²": 71,
|
62 |
+
"á": 57,
|
63 |
+
"ã": 73,
|
64 |
+
"ä": 20,
|
65 |
+
"å": 24,
|
66 |
+
"ç": 64,
|
67 |
+
"é": 49,
|
68 |
+
"í": 54,
|
69 |
+
"ó": 65,
|
70 |
+
"ô": 69,
|
71 |
+
"õ": 59,
|
72 |
+
"ö": 25,
|
73 |
+
"ú": 62,
|
74 |
+
"̇": 66,
|
75 |
+
"–": 61,
|
76 |
+
"”": 52
|
77 |
+
},
|
78 |
+
"tur": {
|
79 |
+
"[PAD]": 36,
|
80 |
+
"[UNK]": 35,
|
81 |
+
"a": 1,
|
82 |
+
"b": 2,
|
83 |
+
"c": 3,
|
84 |
+
"d": 4,
|
85 |
+
"e": 5,
|
86 |
+
"f": 6,
|
87 |
+
"g": 7,
|
88 |
+
"h": 8,
|
89 |
+
"i": 9,
|
90 |
+
"j": 10,
|
91 |
+
"k": 11,
|
92 |
+
"l": 12,
|
93 |
+
"m": 13,
|
94 |
+
"n": 14,
|
95 |
+
"o": 15,
|
96 |
+
"p": 16,
|
97 |
+
"q": 17,
|
98 |
+
"r": 18,
|
99 |
+
"s": 19,
|
100 |
+
"t": 20,
|
101 |
+
"u": 21,
|
102 |
+
"v": 22,
|
103 |
+
"w": 23,
|
104 |
+
"x": 24,
|
105 |
+
"y": 25,
|
106 |
+
"z": 26,
|
107 |
+
"|": 0,
|
108 |
+
"ç": 27,
|
109 |
+
"ë": 28,
|
110 |
+
"ö": 29,
|
111 |
+
"ü": 30,
|
112 |
+
"ğ": 31,
|
113 |
+
"ı": 32,
|
114 |
+
"ş": 33,
|
115 |
+
"̇": 34
|
116 |
+
}
|
117 |
+
}
|