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>": 69, "</s>": 70}
|
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 |
+
{"ل": 0, "ف": 1, "آ": 2, "ض": 3, "ُ": 4, "ۖ": 5, "ﺃ": 6, "ئ": 7, "ر": 8, "ش": 9, "ۚ": 10, "م": 11, "ء": 12, "«": 13, "د": 14, "ً": 15, "خ": 17, "ن": 18, "ت": 19, "ق": 20, "ط": 21, "َ": 22, "،": 23, "س": 24, "ک": 25, "»": 26, "ٰ": 27, "ث": 28, "—": 29, "ع": 30, "ه": 31, "چ": 32, "ة": 33, "ى": 34, "و": 35, "ِ": 36, "ج": 37, "t": 38, "e": 39, "ب": 40, "ظ": 41, "ٌ": 42, "ْ": 43, "غ": 44, "ؤ": 45, "☭": 46, "ك": 47, "_": 48, "؛": 49, "g": 50, "ي": 51, "ص": 52, "ڨ": 53, "ز": 54, "ﻻ": 55, "ذ": 56, "؟": 57, "أ": 58, "ھ": 59, "ـ": 60, "ٍ": 61, "إ": 62, "ّ": 63, "ح": 64, "ی": 65, "ا": 66, "|": 16, "[UNK]": 67, "[PAD]": 68}
|