Upload tokenizer

special_tokens_map.json

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

tokenizer_config.json

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

vocab.json

@@ -0,0 +1,29 @@
+{
+ " ": 2,
+ "'": 5,
+ "-": 24,
+ "_": 18,
+ "a": 26,
+ "b": 1,
+ "c": 4,
+ "d": 10,
+ "e": 3,
+ "f": 6,
+ "g": 14,
+ "h": 25,
+ "i": 13,
+ "j": 9,
+ "k": 19,
+ "l": 8,
+ "m": 16,
+ "n": 11,
+ "o": 21,
+ "q": 15,
+ "r": 12,
+ "s": 23,
+ "t": 17,
+ "u": 0,
+ "w": 7,
+ "x": 22,
+ "y": 20
+}