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 +1,10 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,77 @@
+{
+  "'": 71,
+  "[PAD]": 74,
+  "[UNK]": 73,
+  "a": 35,
+  "b": 14,
+  "c": 25,
+  "d": 12,
+  "e": 32,
+  "f": 54,
+  "g": 40,
+  "h": 21,
+  "i": 39,
+  "j": 38,
+  "k": 27,
+  "l": 30,
+  "m": 53,
+  "n": 23,
+  "o": 34,
+  "p": 72,
+  "q": 15,
+  "r": 43,
+  "s": 9,
+  "t": 5,
+  "u": 64,
+  "v": 18,
+  "w": 69,
+  "x": 47,
+  "y": 36,
+  "z": 48,
+  "|": 62,
+  "ꯀ": 51,
+  "ꯁ": 11,
+  "ꯂ": 45,
+  "ꯃ": 50,
+  "ꯄ": 70,
+  "ꯅ": 13,
+  "ꯆ": 22,
+  "ꯇ": 59,
+  "ꯈ": 63,
+  "ꯉ": 2,
+  "ꯊ": 16,
+  "ꯋ": 41,
+  "ꯌ": 24,
+  "ꯍ": 66,
+  "ꯎ": 42,
+  "ꯏ": 46,
+  "ꯐ": 6,
+  "ꯑ": 3,
+  "ꯒ": 0,
+  "ꯓ": 49,
+  "ꯔ": 52,
+  "ꯕ": 8,
+  "ꯖ": 20,
+  "ꯗ": 44,
+  "ꯘ": 58,
+  "ꯙ": 33,
+  "ꯚ": 17,
+  "ꯛ": 26,
+  "ꯜ": 1,
+  "ꯝ": 60,
+  "ꯞ": 68,
+  "ꯟ": 4,
+  "ꯠ": 55,
+  "ꯡ": 56,
+  "ꯢ": 19,
+  "ꯣ": 65,
+  "ꯤ": 7,
+  "ꯥ": 10,
+  "ꯦ": 29,
+  "ꯧ": 67,
+  "ꯨ": 57,
+  "ꯩ": 37,
+  "ꯪ": 28,
+  "꯬": 31,
+  "꯭": 61
+}