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