Upload tokenizer

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_blank": true,
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "cjs",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "|",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

vocab.json

@@ -0,0 +1,41 @@
+{
+  " ": 38,
+  "-": 30,
+  "|": 0,
+  "а": 1,
+  "б": 22,
+  "в": 32,
+  "г": 23,
+  "д": 10,
+  "е": 2,
+  "ж": 28,
+  "з": 21,
+  "и": 3,
+  "й": 20,
+  "к": 16,
+  "л": 8,
+  "м": 18,
+  "н": 5,
+  "о": 12,
+  "п": 9,
+  "р": 4,
+  "с": 11,
+  "т": 7,
+  "у": 19,
+  "ф": 31,
+  "х": 35,
+  "ц": 37,
+  "ч": 14,
+  "ш": 26,
+  "ы": 6,
+  "ь": 36,
+  "э": 29,
+  "я": 33,
+  "ё": 34,
+  "ғ": 15,
+  "қ": 13,
+  "ң": 17,
+  "ӧ": 27,
+  "ӱ": 25,
+  "–": 24
+}