add tokenizer
Browse files- special_tokens_map.json +6 -0
- tokenizer_config.json +10 -0
- vocab.json +46 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "[UNK]"
|
6 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"pad_token": "[PAD]",
|
6 |
+
"replace_word_delimiter_char": " ",
|
7 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
8 |
+
"unk_token": "[UNK]",
|
9 |
+
"word_delimiter_token": "|"
|
10 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"'": 16,
|
3 |
+
"[PAD]": 43,
|
4 |
+
"[UNK]": 42,
|
5 |
+
"a": 40,
|
6 |
+
"b": 30,
|
7 |
+
"c": 4,
|
8 |
+
"d": 2,
|
9 |
+
"e": 1,
|
10 |
+
"f": 27,
|
11 |
+
"g": 23,
|
12 |
+
"h": 26,
|
13 |
+
"i": 28,
|
14 |
+
"j": 0,
|
15 |
+
"k": 32,
|
16 |
+
"l": 3,
|
17 |
+
"m": 9,
|
18 |
+
"n": 24,
|
19 |
+
"o": 38,
|
20 |
+
"p": 29,
|
21 |
+
"q": 34,
|
22 |
+
"r": 11,
|
23 |
+
"s": 15,
|
24 |
+
"t": 35,
|
25 |
+
"u": 6,
|
26 |
+
"v": 41,
|
27 |
+
"w": 22,
|
28 |
+
"x": 37,
|
29 |
+
"y": 12,
|
30 |
+
"z": 13,
|
31 |
+
"|": 8,
|
32 |
+
"æ": 33,
|
33 |
+
"ð": 14,
|
34 |
+
"ŋ": 7,
|
35 |
+
"ɑ": 31,
|
36 |
+
"ɔ": 25,
|
37 |
+
"ə": 17,
|
38 |
+
"ɛ": 5,
|
39 |
+
"ɪ": 10,
|
40 |
+
"ʃ": 18,
|
41 |
+
"ʊ": 39,
|
42 |
+
"ʒ": 21,
|
43 |
+
"ʤ": 20,
|
44 |
+
"ʧ": 36,
|
45 |
+
"θ": 19
|
46 |
+
}
|