Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 101,
+  "<s>": 100
+}

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "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]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "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": "kaz",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,104 @@
+{
+  "kaz": {
+    "$": 1,
+    "&": 2,
+    "+": 3,
+    "/": 4,
+    "0": 5,
+    "1": 6,
+    "2": 7,
+    "3": 8,
+    "4": 9,
+    "5": 10,
+    "6": 11,
+    "7": 12,
+    "8": 13,
+    "9": 14,
+    "[": 15,
+    "[PAD]": 99,
+    "[UNK]": 98,
+    "]": 16,
+    "a": 17,
+    "b": 18,
+    "c": 19,
+    "d": 20,
+    "e": 21,
+    "f": 22,
+    "g": 23,
+    "h": 24,
+    "i": 25,
+    "j": 26,
+    "k": 27,
+    "l": 28,
+    "m": 29,
+    "n": 30,
+    "o": 31,
+    "p": 32,
+    "q": 33,
+    "r": 34,
+    "s": 35,
+    "t": 36,
+    "u": 37,
+    "v": 38,
+    "w": 39,
+    "x": 40,
+    "y": 41,
+    "z": 42,
+    "|": 0,
+    "«": 43,
+    "°": 44,
+    "»": 45,
+    "½": 46,
+    "¾": 47,
+    "í": 48,
+    "ó": 49,
+    "õ": 50,
+    "ú": 51,
+    "а": 52,
+    "б": 53,
+    "в": 54,
+    "г": 55,
+    "д": 56,
+    "е": 57,
+    "ж": 58,
+    "з": 59,
+    "и": 60,
+    "й": 61,
+    "к": 62,
+    "л": 63,
+    "м": 64,
+    "н": 65,
+    "о": 66,
+    "п": 67,
+    "р": 68,
+    "с": 69,
+    "т": 70,
+    "у": 71,
+    "ф": 72,
+    "х": 73,
+    "ц": 74,
+    "ч": 75,
+    "ш": 76,
+    "щ": 77,
+    "ъ": 78,
+    "ы": 79,
+    "ь": 80,
+    "э": 81,
+    "ю": 82,
+    "я": 83,
+    "ё": 84,
+    "і": 85,
+    "ғ": 86,
+    "қ": 87,
+    "ң": 88,
+    "ү": 89,
+    "ұ": 90,
+    "һ": 91,
+    "ә": 92,
+    "ө": 93,
+    "​": 94,
+    "–": 95,
+    "—": 96,
+    "№": 97
+  }
+}