Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 37,
+  "<s>": 36
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "34": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "tat",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,40 @@
+{
+  "tat": {
+    "[PAD]": 35,
+    "[UNK]": 34,
+    "|": 0,
+    "а": 1,
+    "б": 2,
+    "в": 3,
+    "г": 4,
+    "д": 5,
+    "е": 6,
+    "з": 7,
+    "и": 8,
+    "к": 9,
+    "л": 10,
+    "м": 11,
+    "н": 12,
+    "о": 13,
+    "п": 14,
+    "р": 15,
+    "с": 16,
+    "т": 17,
+    "у": 18,
+    "ф": 19,
+    "х": 20,
+    "ч": 21,
+    "ш": 22,
+    "ы": 23,
+    "ь": 24,
+    "э": 25,
+    "ю": 26,
+    "я": 27,
+    "җ": 28,
+    "ң": 29,
+    "ү": 30,
+    "һ": 31,
+    "ә": 32,
+    "ө": 33
+  }
+}