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