anah1tbaghdassarian
commited on
Upload tokenizer
Browse files- added_tokens.json +2 -3
- special_tokens_map.json +1 -1
- tokenizer_config.json +7 -8
- vocab.json +1 -0
added_tokens.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"<s>": 41
|
5 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 43,
|
3 |
+
"<s>": 42
|
|
|
4 |
}
|
special_tokens_map.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"bos_token": "<s>",
|
3 |
"eos_token": "</s>",
|
4 |
-
"pad_token": "
|
5 |
"unk_token": "[UNK]"
|
6 |
}
|
|
|
1 |
{
|
2 |
"bos_token": "<s>",
|
3 |
"eos_token": "</s>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
"unk_token": "[UNK]"
|
6 |
}
|
tokenizer_config.json
CHANGED
@@ -9,15 +9,15 @@
|
|
9 |
"special": false
|
10 |
},
|
11 |
"41": {
|
12 |
-
"content": "
|
13 |
-
"lstrip":
|
14 |
"normalized": false,
|
15 |
-
"rstrip":
|
16 |
"single_word": false,
|
17 |
-
"special":
|
18 |
},
|
19 |
"42": {
|
20 |
-
"content": "
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
@@ -25,7 +25,7 @@
|
|
25 |
"special": true
|
26 |
},
|
27 |
"43": {
|
28 |
-
"content": "
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
@@ -38,8 +38,7 @@
|
|
38 |
"do_lower_case": false,
|
39 |
"eos_token": "</s>",
|
40 |
"model_max_length": 1000000000000000019884624838656,
|
41 |
-
"pad_token": "
|
42 |
-
"processor_class": "Wav2Vec2Processor",
|
43 |
"replace_word_delimiter_char": " ",
|
44 |
"target_lang": null,
|
45 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
9 |
"special": false
|
10 |
},
|
11 |
"41": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": true,
|
14 |
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
"single_word": false,
|
17 |
+
"special": false
|
18 |
},
|
19 |
"42": {
|
20 |
+
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
|
|
25 |
"special": true
|
26 |
},
|
27 |
"43": {
|
28 |
+
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
|
|
38 |
"do_lower_case": false,
|
39 |
"eos_token": "</s>",
|
40 |
"model_max_length": 1000000000000000019884624838656,
|
41 |
+
"pad_token": "[PAD]",
|
|
|
42 |
"replace_word_delimiter_char": " ",
|
43 |
"target_lang": null,
|
44 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
vocab.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"[UNK]": 40,
|
3 |
"|": 0,
|
4 |
"ա": 1,
|
|
|
1 |
{
|
2 |
+
"[PAD]": 41,
|
3 |
"[UNK]": 40,
|
4 |
"|": 0,
|
5 |
"ա": 1,
|