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