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