add tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 38,
+  "<s>": 37
+}

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "name_or_path": "./",
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,39 @@
+{
+  "[PAD]": 0,
+  "[UNK]": 1,
+  "|": 2,
+  "а": 3,
+  "б": 4,
+  "в": 5,
+  "г": 6,
+  "д": 7,
+  "е": 8,
+  "ж": 10,
+  "з": 11,
+  "и": 12,
+  "й": 13,
+  "к": 14,
+  "л": 15,
+  "м": 16,
+  "н": 17,
+  "о": 18,
+  "п": 20,
+  "р": 21,
+  "с": 22,
+  "т": 23,
+  "у": 24,
+  "ф": 26,
+  "х": 27,
+  "ц": 28,
+  "ч": 29,
+  "ш": 30,
+  "ъ": 31,
+  "ы": 32,
+  "ь": 33,
+  "э": 34,
+  "ю": 35,
+  "я": 36,
+  "ё": 9,
+  "ү": 25,
+  "ө": 19
+}