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