Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "41": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "42": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "is_uroman": false,
+  "language": "rus",
+  "model_max_length": 1536,
+  "normalize": false,
+  "pad_token": "<pad>",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

vocab.json

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