Upload tokenizer

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 35
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "mos",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "|",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,37 @@
+{
+  " ": 34,
+  "'": 31,
+  "-": 19,
+  "6": 33,
+  "a": 1,
+  "b": 4,
+  "d": 10,
+  "e": 3,
+  "f": 26,
+  "g": 6,
+  "i": 14,
+  "k": 15,
+  "l": 11,
+  "m": 5,
+  "n": 2,
+  "o": 8,
+  "p": 23,
+  "r": 17,
+  "s": 7,
+  "t": 12,
+  "u": 24,
+  "v": 30,
+  "w": 21,
+  "y": 9,
+  "z": 22,
+  "|": 0,
+  "ã": 16,
+  "õ": 25,
+  "ĩ": 29,
+  "ũ": 28,
+  "ɛ": 27,
+  "ɩ": 18,
+  "ʋ": 20,
+  "ẽ": 13,
+  "–": 32
+}