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