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 @@
+{"а": 0, "ц": 1, "ч": 2, "г": 3, "б": 4, "э": 5, "с": 6, "о": 7, "ф": 8, "д": 9, "у": 10, "и": 11, "й": 12, "ё": 13, "ш": 14, "в": 15, "н": 17, "х": 18, "л": 19, "к": 20, "м": 21, "я": 22, "ю": 23, "з": 24, "ы": 25, "ж": 26, "р": 27, "ъ": 28, "ь": 29, "т": 30, "п": 31, "е": 32, "щ": 33, "|": 16, "[UNK]": 34, "[PAD]": 35}