Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 41,
+  "<s>": 40
+}

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": {
+    "38": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "41": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "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": "ky",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,44 @@
+{
+  "ky": {
+    "[PAD]": 39,
+    "[UNK]": 38,
+    "|": 0,
+    "а": 1,
+    "б": 2,
+    "в": 3,
+    "г": 4,
+    "д": 5,
+    "е": 6,
+    "ж": 7,
+    "з": 8,
+    "и": 9,
+    "й": 10,
+    "к": 11,
+    "л": 12,
+    "м": 13,
+    "н": 14,
+    "о": 15,
+    "п": 16,
+    "р": 17,
+    "с": 18,
+    "т": 19,
+    "у": 20,
+    "ф": 21,
+    "х": 22,
+    "ц": 23,
+    "ч": 24,
+    "ш": 25,
+    "щ": 26,
+    "ъ": 27,
+    "ы": 28,
+    "ь": 29,
+    "э": 30,
+    "ю": 31,
+    "я": 32,
+    "ё": 33,
+    "ң": 34,
+    "ү": 35,
+    "ӊ": 36,
+    "ө": 37
+  }
+}