Commit
•
f0ec284
1
Parent(s):
ca85016
Upload tokenizer
Browse files- added_tokens.json +4 -0
- special_tokens_map.json +30 -0
- tokenizer_config.json +48 -0
- vocab.json +38 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 37,
|
3 |
+
"<s>": 36
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": true,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": true,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "[UNK]",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": true,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"34": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"35": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
+
"single_word": false,
|
17 |
+
"special": false
|
18 |
+
},
|
19 |
+
"36": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"37": {
|
28 |
+
"content": "</s>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"bos_token": "<s>",
|
37 |
+
"clean_up_tokenization_spaces": true,
|
38 |
+
"do_lower_case": false,
|
39 |
+
"eos_token": "</s>",
|
40 |
+
"model_max_length": 1000000000000000019884624838656,
|
41 |
+
"pad_token": "[PAD]",
|
42 |
+
"processor_class": "Wav2Vec2Processor",
|
43 |
+
"replace_word_delimiter_char": " ",
|
44 |
+
"target_lang": null,
|
45 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
46 |
+
"unk_token": "[UNK]",
|
47 |
+
"word_delimiter_token": "|"
|
48 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"0": 1,
|
3 |
+
"1": 2,
|
4 |
+
"2": 3,
|
5 |
+
"3": 4,
|
6 |
+
"4": 5,
|
7 |
+
"5": 6,
|
8 |
+
"7": 7,
|
9 |
+
"9": 8,
|
10 |
+
"[PAD]": 35,
|
11 |
+
"[UNK]": 34,
|
12 |
+
"a": 9,
|
13 |
+
"b": 10,
|
14 |
+
"c": 11,
|
15 |
+
"d": 12,
|
16 |
+
"e": 13,
|
17 |
+
"f": 14,
|
18 |
+
"g": 15,
|
19 |
+
"h": 16,
|
20 |
+
"i": 17,
|
21 |
+
"j": 18,
|
22 |
+
"k": 19,
|
23 |
+
"l": 20,
|
24 |
+
"m": 21,
|
25 |
+
"n": 22,
|
26 |
+
"o": 23,
|
27 |
+
"p": 24,
|
28 |
+
"r": 25,
|
29 |
+
"s": 26,
|
30 |
+
"t": 27,
|
31 |
+
"u": 28,
|
32 |
+
"v": 29,
|
33 |
+
"w": 30,
|
34 |
+
"x": 31,
|
35 |
+
"y": 32,
|
36 |
+
"z": 33,
|
37 |
+
"|": 0
|
38 |
+
}
|