muratsimsek003
commited on
Commit
•
b5f87c3
1
Parent(s):
e01d82a
Update tokenizer_config.json
Browse files- tokenizer_config.json +1 -50
tokenizer_config.json
CHANGED
@@ -1,50 +1 @@
|
|
1 |
-
{
|
2 |
-
"added_tokens_decoder": {
|
3 |
-
"0": {
|
4 |
-
"content": "<pad>",
|
5 |
-
"lstrip": true,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": true,
|
8 |
-
"single_word": false,
|
9 |
-
"special": false
|
10 |
-
},
|
11 |
-
"1": {
|
12 |
-
"content": "<s>",
|
13 |
-
"lstrip": true,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": true,
|
16 |
-
"single_word": false,
|
17 |
-
"special": false
|
18 |
-
},
|
19 |
-
"2": {
|
20 |
-
"content": "</s>",
|
21 |
-
"lstrip": true,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": true,
|
24 |
-
"single_word": false,
|
25 |
-
"special": false
|
26 |
-
},
|
27 |
-
"3": {
|
28 |
-
"content": "<unk>",
|
29 |
-
"lstrip": true,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": true,
|
32 |
-
"single_word": false,
|
33 |
-
"special": false
|
34 |
-
}
|
35 |
-
},
|
36 |
-
"bos_token": "<s>",
|
37 |
-
"clean_up_tokenization_spaces": true,
|
38 |
-
"do_lower_case": false,
|
39 |
-
"do_normalize": true,
|
40 |
-
"eos_token": "</s>",
|
41 |
-
"model_max_length": 1000000000000000019884624838656,
|
42 |
-
"pad_token": "<pad>",
|
43 |
-
"processor_class": "Wav2Vec2Processor",
|
44 |
-
"replace_word_delimiter_char": " ",
|
45 |
-
"return_attention_mask": false,
|
46 |
-
"target_lang": null,
|
47 |
-
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
48 |
-
"unk_token": "<unk>",
|
49 |
-
"word_delimiter_token": "|"
|
50 |
-
}
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|