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