Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 37,
+  "<s>": 36
+}

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 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "34": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "azj-script_latin",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,40 @@
+{
+  "azj-script_latin": {
+    "[PAD]": 35,
+    "[UNK]": 34,
+    "a": 1,
+    "b": 2,
+    "c": 3,
+    "d": 4,
+    "e": 5,
+    "f": 6,
+    "g": 7,
+    "h": 8,
+    "i": 9,
+    "j": 10,
+    "k": 11,
+    "l": 12,
+    "m": 13,
+    "n": 14,
+    "o": 15,
+    "p": 16,
+    "q": 17,
+    "r": 18,
+    "s": 19,
+    "t": 20,
+    "u": 21,
+    "v": 22,
+    "x": 23,
+    "y": 24,
+    "z": 25,
+    "|": 0,
+    "ç": 26,
+    "ö": 27,
+    "ü": 28,
+    "ğ": 29,
+    "ı": 30,
+    "ş": 31,
+    "ə": 32,
+    "̇": 33
+  }
+}