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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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