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>": 68, "</s>": 69}
|
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 |
+
{"ر": 0, "ى": 1, "ِ": 2, "ل": 3, "د": 4, "غ": 5, "ؤ": 6, "و": 7, "ة": 8, "ٌ": 9, "ه": 10, "”": 11, "ف": 12, "ج": 13, "☭": 14, "“": 15, "ـ": 16, "ک": 17, "ڨ": 18, "،": 19, "ئ": 20, "ص": 21, "إ": 22, "ء": 23, "ا": 24, "ن": 25, "آ": 26, "ُ": 27, "ذ": 28, "س": 29, "چ": 30, "م": 31, "ك": 32, "ﻻ": 33, "؛": 34, "—": 35, "»": 36, "ﺃ": 37, "ۖ": 38, "_": 39, "ق": 40, "ي": 41, "«": 42, "ث": 43, "ز": 44, "ٍ": 45, "ی": 46, "ٰ": 48, "أ": 49, "َ": 50, "ح": 51, "ض": 52, "ش": 53, "خ": 54, "ّ": 55, "ع": 56, "؟": 57, "ً": 58, "ھ": 59, "ط": 60, "ظ": 61, "ۚ": 62, "ت": 63, "ْ": 64, "ب": 65, "|": 47, "[UNK]": 66, "[PAD]": 67}
|