Commit
•
5bf99be
1
Parent(s):
378939c
add tokenizer
Browse files- added_tokens.json +1 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<s>": 55, "</s>": 56}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"ء": 1, "آ": 2, "ؤ": 3, "ئ": 4, "ا": 5, "ب": 6, "ت": 7, "ث": 8, "ج": 9, "ح": 10, "خ": 11, "د": 12, "ذ": 13, "ر": 14, "ز": 15, "س": 16, "ش": 17, "ص": 18, "ض": 19, "ط": 20, "ظ": 21, "ع": 22, "غ": 23, "ف": 24, "ق": 25, "ل": 26, "م": 27, "ن": 28, "و": 29, "ى": 30, "ي": 31, "ً": 32, "َ": 33, "ُ": 34, "ِ": 35, "ّ": 36, "ٔ": 37, "ٰ": 38, "ٹ": 39, "پ": 40, "چ": 41, "ڈ": 42, "ڑ": 43, "ژ": 44, "ک": 45, "گ": 46, "ں": 47, "ھ": 48, "ہ": 49, "ۂ": 50, "ی": 51, "ے": 52, "|": 0, "[UNK]": 53, "[PAD]": 54}
|