Commit
•
0e5ea75
1
Parent(s):
261ff2c
add tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
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": "/workspace/.cache/huggingface/transformers/898afae2faf3d20dd22149b80863bb5d448c67d9c9b821dd66753253a4d77c64.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd", "tokenizer_file": null, "name_or_path": "Harveenchadha/vakyansh-wav2vec2-urdu-urm-60", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<s>": 0, "<pad>": 1, "</s>": 2, "<unk>": 3, "|": 4, "ء": 5, "آ": 6, "ؤ": 7, "ئ": 8, "ا": 9, "ب": 10, "ت": 11, "ث": 12, "ج": 13, "ح": 14, "خ": 15, "د": 16, "ذ": 17, "ر": 18, "ز": 19, "س": 20, "ش": 21, "ص": 22, "ض": 23, "ط": 24, "ظ": 25, "ع": 26, "غ": 27, "ف": 28, "ق": 29, "ل": 30, "م": 31, "ن": 32, "و": 33, "ٹ": 34, "پ": 35, "چ": 36, "ڈ": 37, "ڑ": 38, "ژ": 39, "ک": 40, "گ": 41, "ں": 42, "ھ": 43, "ہ": 44, "ی": 45, "ے": 46, "ۓ": 47}
|