tlsalfm820
commited on
Commit
•
43dd782
1
Parent(s):
bf8633e
Upload tokenizer
Browse files- special_tokens_map.json +6 -0
- tokenizer_config.json +12 -0
- vocab.json +32 -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 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
10 |
+
"unk_token": "[UNK]",
|
11 |
+
"word_delimiter_token": "|"
|
12 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"'": 22,
|
3 |
+
"[PAD]": 29,
|
4 |
+
"[UNK]": 28,
|
5 |
+
"a": 15,
|
6 |
+
"b": 5,
|
7 |
+
"c": 26,
|
8 |
+
"d": 11,
|
9 |
+
"e": 17,
|
10 |
+
"f": 7,
|
11 |
+
"g": 10,
|
12 |
+
"h": 18,
|
13 |
+
"i": 25,
|
14 |
+
"j": 23,
|
15 |
+
"k": 4,
|
16 |
+
"l": 9,
|
17 |
+
"m": 24,
|
18 |
+
"n": 14,
|
19 |
+
"o": 20,
|
20 |
+
"p": 21,
|
21 |
+
"q": 12,
|
22 |
+
"r": 1,
|
23 |
+
"s": 16,
|
24 |
+
"t": 19,
|
25 |
+
"u": 27,
|
26 |
+
"v": 8,
|
27 |
+
"w": 6,
|
28 |
+
"x": 2,
|
29 |
+
"y": 3,
|
30 |
+
"z": 13,
|
31 |
+
"|": 0
|
32 |
+
}
|