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 @@
+{"i": 0, "ź": 1, "ż": 2, "'": 3, "b": 4, "t": 5, "ń": 6, "g": 7, "x": 8, "s": 9, "p": 10, "ł": 11, "e": 12, "f": 13, "o": 14, "ś": 15, "j": 16, "d": 17, "k": 18, "l": 19, "a": 20, "n": 21, "ę": 22, "h": 23, "c": 24, "q": 25, "ą": 26, "m": 27, "r": 28, "ó": 29, "v": 30, "w": 32, "ć": 33, "y": 34, "z": 35, "u": 36, "|": 31, "[UNK]": 37, "[PAD]": 38}