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, "v": 1, "u": 2, "o": 3, "k": 4, "y": 5, "g": 6, "r": 7, "t": 8, "h": 9, "e": 10, "q": 11, "p": 12, "c": 13, "l": 14, "j": 15, "n": 17, "'": 18, "x": 19, "i": 20, "d": 21, "m": 22, "b": 23, "s": 24, "a": 25, "w": 26, "z": 27, "|": 16, "[UNK]": 28, "[PAD]": 29}