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": "khm",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "្",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

vocab.json

@@ -0,0 +1,76 @@
+{
+  " ": 19,
+  "-": 71,
+  "1": 57,
+  "_": 36,
+  "q": 15,
+  "ក": 38,
+  "ខ": 62,
+  "គ": 4,
+  "ឃ": 9,
+  "ង": 5,
+  "ច": 54,
+  "ឆ": 3,
+  "ជ": 20,
+  "ឈ": 14,
+  "ញ": 64,
+  "ដ": 42,
+  "ឋ": 55,
+  "ឌ": 10,
+  "ណ": 56,
+  "ត": 35,
+  "ថ": 68,
+  "ទ": 24,
+  "ធ": 7,
+  "ន": 59,
+  "ប": 12,
+  "ផ": 17,
+  "ព": 52,
+  "ភ": 73,
+  "ម": 72,
+  "យ": 1,
+  "រ": 26,
+  "ល": 22,
+  "វ": 43,
+  "ស": 61,
+  "ហ": 58,
+  "ឡ": 53,
+  "អ": 2,
+  "ឥ": 11,
+  "ឧ": 21,
+  "ឪ": 70,
+  "ឫ": 46,
+  "ឬ": 45,
+  "ឭ": 28,
+  "ឮ": 66,
+  "ឯ": 51,
+  "ឱ": 23,
+  "ា": 29,
+  "ិ": 18,
+  "ី": 49,
+  "ឹ": 60,
+  "ឺ": 69,
+  "ុ": 50,
+  "ូ": 25,
+  "ួ": 13,
+  "ើ": 6,
+  "ឿ": 31,
+  "ៀ": 30,
+  "េ": 32,
+  "ែ": 39,
+  "ៃ": 41,
+  "ោ": 48,
+  "ៅ": 40,
+  "ំ": 33,
+  "ះ": 47,
+  "ៈ": 44,
+  "៉": 37,
+  "៊": 65,
+  "់": 8,
+  "៌": 67,
+  "៍": 34,
+  "៎": 27,
+  "៏": 16,
+  "័": 63,
+  "្": 0
+}