Commit
•
6fa3745
1
Parent(s):
9f53969
add tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -1
- vocab.json +1 -1
special_tokens_map.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"unk_token": "
|
|
|
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/output_models/fa/xlsr-fa/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "m3hrdadfi/wav2vec2-large-xlsr-persian-v3", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "آ": 5, "ئ": 6, "ا": 7, "ب": 8, "ت": 9, "ث": 10, "ج": 11, "ح": 12, "خ": 13, "د": 14, "ذ": 15, "ر": 16, "ز": 17, "س": 18, "ش": 19, "ص": 20, "ض": 21, "ط": 22, "ظ": 23, "ع": 24, "غ": 25, "ف": 26, "ق": 27, "ل": 28, "م": 29, "ن": 30, "ه": 31, "و": 32, "پ": 33, "چ": 34, "ژ": 35, "ک": 36, "گ": 37, "ی": 38, "": 39}
|