add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 34, "</s>": 35}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"l": 0, "p": 1, "t": 2, "y": 4, "o": 5, "i": 6, "š": 7, "r": 8, "j": 9, "z": 10, "f": 11, "ž": 12, "g": 13, "«": 14, "–": 15, "e": 16, "a": 17, "h": 18, "c": 19, "w": 20, "d": 21, "č": 22, "k": 23, "x": 24, "s": 25, "n": 26, "m": 27, "»": 28, "b": 29, "v": 30, "u": 31, "|": 3, "[UNK]": 32, "[PAD]": 33}