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