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