Upload tokenizer
Browse files- added_tokens.json +4 -1
- special_tokens_map.json +22 -1
- tokenizer_config.json +11 -1
- vocab.json +1 -1
added_tokens.json
CHANGED
@@ -1 +1,4 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 41,
|
3 |
+
"<s>": 40
|
4 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1 +1,22 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "</s>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"bos_token": "<s>",
|
19 |
+
"eos_token": "</s>",
|
20 |
+
"pad_token": "[PAD]",
|
21 |
+
"unk_token": "[UNK]"
|
22 |
+
}
|
tokenizer_config.json
CHANGED
@@ -1 +1,11 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"name_or_path": "./",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"special_tokens_map_file": null,
|
8 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
9 |
+
"unk_token": "[UNK]",
|
10 |
+
"word_delimiter_token": "|"
|
11 |
+
}
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"ğ": 0, "y": 1, "h": 2, "l": 3, "a": 4, "̇": 5, "r": 6, "ë": 7, "w": 8, "i": 9, "n": 10, "â": 11, "'": 12, "e": 13, "ü": 14, "ö": 15, "d": 16, "g": 17, "î": 18, "b": 19, "m": 20, "s": 21, "f": 22, "x": 23, "c": 24, "j": 25, "u": 26, "v": 27, "o": 28, "z": 29, "q": 30, "t": 32, "ç": 33, "ş": 34, "p": 35, "ı": 36, "k": 37, "|": 31, "[UNK]": 38, "[PAD]": 39}
|