Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 36,
+  "<s>": 35
+}

special_tokens_map.json

@@ -1,4 +1,20 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": "<s>",
   "eos_token": "</s>",
   "pad_token": "[PAD]",

tokenizer_config.json

@@ -1,10 +1,13 @@
 {
   "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": false,
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
+  "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"

vocab.json

@@ -1,32 +1,37 @@
 {
-  "[PAD]": 29,
-  "[UNK]": 28,
-  "a": 23,
-  "b": 22,
-  "d": 0,
-  "f": 16,
-  "h": 15,
-  "i": 20,
-  "j": 19,
-  "k": 1,
-  "l": 6,
-  "m": 26,
-  "n": 8,
-  "q": 4,
-  "r": 9,
-  "s": 2,
-  "t": 3,
-  "u": 18,
-  "w": 27,
-  "x": 12,
-  "|": 21,
-  "ð": 17,
-  "ħ": 10,
-  "ɣ": 5,
-  "ʃ": 25,
-  "ʒ": 13,
-  "ʔ": 11,
-  "ʕ": 14,
-  "ː": 24,
-  "ˤ": 7
+  "[PAD]": 34,
+  "[UNK]": 33,
+  "|": 0,
+  "ء": 1,
+  "آ": 2,
+  "أ": 3,
+  "إ": 4,
+  "ا": 5,
+  "ب": 6,
+  "ة": 7,
+  "ت": 8,
+  "ج": 9,
+  "ح": 10,
+  "خ": 11,
+  "د": 12,
+  "ذ": 13,
+  "ر": 14,
+  "س": 15,
+  "ش": 16,
+  "ص": 17,
+  "ض": 18,
+  "ط": 19,
+  "ظ": 20,
+  "ع": 21,
+  "غ": 22,
+  "ف": 23,
+  "ق": 24,
+  "ك": 25,
+  "ل": 26,
+  "م": 27,
+  "ن": 28,
+  "ه": 29,
+  "و": 30,
+  "ى": 31,
+  "ي": 32
 }