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 @@
+{"ƴ": 0, "s": 1, "k": 2, "ɓ": 3, "“": 4, "d": 5, "y": 6, "x": 7, "z": 8, "j": 9, "u": 10, "t": 11, "o": 12, "c": 13, "n": 14, "i": 15, "h": 16, "b": 17, "e": 18, "ɗ": 19, "w": 20, "g": 21, "’": 22, "ƙ": 23, "ʻ": 24, "”": 26, "m": 27, "v": 28, "a": 29, "—": 30, "í": 31, "l": 32, "f": 33, "p": 34, "q": 35, "'": 36, "r": 37, "|": 25, "[UNK]": 38, "[PAD]": 39}