Upload tokenizer

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 44,
+  "<s>": 43,
+  "<unk>": 45
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "44": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "45": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "phonemes",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,98 @@
+{
+  "ghonna": {
+    "[PAD]": 0,
+    "[لا غنة]": 2,
+    "[مغن]": 1
+  },
+  "hams_or_jahr": {
+    "[PAD]": 0,
+    "[جهر]": 2,
+    "[همس]": 1
+  },
+  "istitala": {
+    "[PAD]": 0,
+    "[لا إستطالة]": 2,
+    "[مستطيل]": 1
+  },
+  "itbaq": {
+    "[PAD]": 0,
+    "[مطبق]": 2,
+    "[مفخم]": 1
+  },
+  "phonemes": {
+    "[PAD]": 0,
+    "ؙ": 42,
+    "ء": 1,
+    "ا": 29,
+    "ب": 2,
+    "ت": 3,
+    "ث": 4,
+    "ج": 5,
+    "ح": 6,
+    "خ": 7,
+    "د": 8,
+    "ذ": 9,
+    "ر": 10,
+    "ز": 11,
+    "س": 12,
+    "ش": 13,
+    "ص": 14,
+    "ض": 15,
+    "ط": 16,
+    "ظ": 17,
+    "ع": 18,
+    "غ": 19,
+    "ـ": 36,
+    "ف": 20,
+    "ق": 21,
+    "ك": 22,
+    "ل": 23,
+    "م": 24,
+    "ن": 25,
+    "ه": 26,
+    "و": 27,
+    "ي": 28,
+    "َ": 32,
+    "ُ": 33,
+    "ِ": 34,
+    "ٲ": 37,
+    "ڇ": 38,
+    "ں": 39,
+    "ۜ": 41,
+    "ۥ": 31,
+    "ۦ": 30,
+    "۪": 35,
+    "۾": 40
+  },
+  "qalqla": {
+    "[PAD]": 0,
+    "[لا قلقلة]": 2,
+    "[مقلقل]": 1
+  },
+  "safeer": {
+    "[PAD]": 0,
+    "[صفير]": 1,
+    "[لا صفير]": 2
+  },
+  "shidda_or_rakhawa": {
+    "[PAD]": 0,
+    "[بين الشدة والرخاوة]": 2,
+    "[رخو]": 3,
+    "[شديد]": 1
+  },
+  "tafashie": {
+    "[PAD]": 0,
+    "[لا تفشي]": 2,
+    "[متفشي]": 1
+  },
+  "tafkheem_or_taqeeq": {
+    "[PAD]": 0,
+    "[مرقق]": 2,
+    "[مفخم]": 1
+  },
+  "tikraar": {
+    "[PAD]": 0,
+    "[لا تكرار]": 2,
+    "[مكرر]": 1
+  }
+}