Upload tokenizer

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 +1,13 @@
+{
+  "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": "sah",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,44 @@
+{
+  "sah": {
+    "-": 4,
+    "<pad>": 39,
+    "<unk>": 38,
+    "y": 34,
+    "|": 5,
+    "а": 32,
+    "б": 33,
+    "в": 7,
+    "г": 17,
+    "д": 28,
+    "е": 2,
+    "ж": 26,
+    "з": 20,
+    "и": 12,
+    "й": 8,
+    "к": 22,
+    "л": 30,
+    "м": 10,
+    "н": 15,
+    "о": 1,
+    "п": 3,
+    "р": 13,
+    "с": 24,
+    "т": 14,
+    "у": 36,
+    "ф": 31,
+    "х": 25,
+    "ц": 0,
+    "ч": 27,
+    "ш": 29,
+    "щ": 6,
+    "ы": 9,
+    "ь": 37,
+    "э": 11,
+    "я": 19,
+    "ҕ": 21,
+    "ҥ": 35,
+    "ү": 16,
+    "һ": 18,
+    "ө": 23
+  }
+}