Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 40,
+  "<s>": 39
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "37": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "40": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,41 @@
+{
+  "[PAD]": 38,
+  "[UNK]": 37,
+  "|": 13,
+  "ა": 5,
+  "ბ": 14,
+  "გ": 11,
+  "დ": 9,
+  "ე": 22,
+  "ვ": 33,
+  "ზ": 23,
+  "თ": 7,
+  "ი": 6,
+  "კ": 17,
+  "ლ": 28,
+  "მ": 1,
+  "ნ": 27,
+  "ო": 20,
+  "პ": 0,
+  "ჟ": 8,
+  "რ": 24,
+  "ს": 19,
+  "ტ": 16,
+  "უ": 29,
+  "ფ": 4,
+  "ქ": 36,
+  "ღ": 32,
+  "ყ": 34,
+  "შ": 2,
+  "ჩ": 35,
+  "ც": 18,
+  "ძ": 31,
+  "წ": 30,
+  "ჭ": 3,
+  "ხ": 12,
+  "ჯ": 26,
+  "ჰ": 21,
+  "–": 15,
+  "—": 10,
+  "„": 25
+}