add tokenizer

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"x": 0, "p": 1, "v": 2, "z": 3, "j": 4, "w": 5, "ɓ": 6, "l": 7, "f": 8, "t": 9, "k": 10, "n": 11, "g": 12, "s": 13, "c": 14, "d": 15, "í": 16, "b": 17, "ƙ": 18, "ƴ": 20, "h": 21, "’": 22, "ʻ": 24, "m": 25, "y": 26, "ɗ": 27, "i": 28, "'": 29, "r": 30, "o": 31, "e": 32, "a": 33, "q": 34, "u": 35, "|": 19, "/": 23, "[UNK]": 36, "[PAD]": 37}