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