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

vocab.json

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