Upload tokenizer
Browse files- special_tokens_map.json +6 -0
- tokenizer_config.json +13 -0
- vocab.json +35 -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 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"replace_word_delimiter_char": " ",
|
9 |
+
"target_lang": null,
|
10 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
11 |
+
"unk_token": "[UNK]",
|
12 |
+
"word_delimiter_token": "|"
|
13 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
",": 7,
|
3 |
+
"-": 27,
|
4 |
+
"0": 9,
|
5 |
+
"1": 21,
|
6 |
+
"2": 29,
|
7 |
+
"?": 30,
|
8 |
+
"A": 1,
|
9 |
+
"B": 11,
|
10 |
+
"C": 22,
|
11 |
+
"D": 3,
|
12 |
+
"E": 6,
|
13 |
+
"F": 12,
|
14 |
+
"G": 13,
|
15 |
+
"H": 25,
|
16 |
+
"I": 23,
|
17 |
+
"J": 8,
|
18 |
+
"K": 0,
|
19 |
+
"L": 17,
|
20 |
+
"M": 14,
|
21 |
+
"N": 2,
|
22 |
+
"O": 5,
|
23 |
+
"P": 16,
|
24 |
+
"R": 24,
|
25 |
+
"S": 19,
|
26 |
+
"T": 28,
|
27 |
+
"U": 4,
|
28 |
+
"V": 10,
|
29 |
+
"W": 15,
|
30 |
+
"Y": 26,
|
31 |
+
"Z": 20,
|
32 |
+
"[PAD]": 32,
|
33 |
+
"[UNK]": 31,
|
34 |
+
"|": 18
|
35 |
+
}
|