Upload tokenizer

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 43
+}

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "pad_token": "р",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "р",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "43": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "kaz",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "р",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,45 @@
+{
+  " ": 38,
+  "-": 7,
+  "_": 13,
+  "а": 18,
+  "б": 3,
+  "в": 12,
+  "г": 32,
+  "д": 28,
+  "е": 25,
+  "ж": 26,
+  "з": 20,
+  "и": 36,
+  "й": 11,
+  "к": 14,
+  "л": 15,
+  "м": 19,
+  "н": 39,
+  "о": 37,
+  "п": 27,
+  "р": 0,
+  "с": 40,
+  "т": 1,
+  "у": 5,
+  "ф": 30,
+  "х": 21,
+  "ц": 17,
+  "ш": 10,
+  "щ": 24,
+  "ы": 9,
+  "ь": 6,
+  "э": 31,
+  "ю": 8,
+  "я": 41,
+  "і": 34,
+  "ғ": 35,
+  "қ": 33,
+  "ң": 16,
+  "ү": 4,
+  "ұ": 2,
+  "һ": 23,
+  "ә": 22,
+  "ө": 42,
+  "—": 29
+}