Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": " "
+}

vocab.json

@@ -0,0 +1,104 @@
+{
+  " ": 0,
+  "'": 1,
+  "[PAD]": 101,
+  "[UNK]": 100,
+  "_": 2,
+  "a": 3,
+  "b": 4,
+  "c": 5,
+  "e": 6,
+  "f": 7,
+  "g": 8,
+  "h": 9,
+  "i": 10,
+  "j": 11,
+  "k": 12,
+  "l": 13,
+  "m": 14,
+  "n": 15,
+  "o": 16,
+  "p": 17,
+  "r": 18,
+  "s": 19,
+  "t": 20,
+  "u": 21,
+  "w": 22,
+  "x": 23,
+  "y": 24,
+  "|": 25,
+  "~": 26,
+  "ก": 27,
+  "ข": 28,
+  "ฃ": 29,
+  "ค": 30,
+  "ฆ": 31,
+  "ง": 32,
+  "จ": 33,
+  "ฉ": 34,
+  "ช": 35,
+  "ซ": 36,
+  "ฌ": 37,
+  "ญ": 38,
+  "ฎ": 39,
+  "ฏ": 40,
+  "ฐ": 41,
+  "ฑ": 42,
+  "ฒ": 43,
+  "ณ": 44,
+  "ด": 45,
+  "ต": 46,
+  "ถ": 47,
+  "ท": 48,
+  "ธ": 49,
+  "น": 50,
+  "บ": 51,
+  "ป": 52,
+  "ผ": 53,
+  "ฝ": 54,
+  "พ": 55,
+  "ฟ": 56,
+  "ภ": 57,
+  "ม": 58,
+  "ย": 59,
+  "ร": 60,
+  "ฤ": 61,
+  "ล": 62,
+  "ว": 63,
+  "ศ": 64,
+  "ษ": 65,
+  "ส": 66,
+  "ห": 67,
+  "ฬ": 68,
+  "อ": 69,
+  "ฮ": 70,
+  "ฯ": 71,
+  "ะ": 72,
+  "ั": 73,
+  "า": 74,
+  "ำ": 75,
+  "ิ": 76,
+  "ี": 77,
+  "ึ": 78,
+  "ื": 79,
+  "ุ": 80,
+  "ู": 81,
+  "เ": 82,
+  "แ": 83,
+  "โ": 84,
+  "ใ": 85,
+  "ไ": 86,
+  "ๅ": 87,
+  "็": 88,
+  "่": 89,
+  "้": 90,
+  "๊": 91,
+  "๋": 92,
+  "์": 93,
+  "ํ": 94,
+  "—": 95,
+  "‘": 96,
+  "’": 97,
+  "“": 98,
+  "”": 99
+}