Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 32,
-  "<s>": 31
+  "</s>": 38,
+  "<s>": 37
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "29": {
+    "35": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "30": {
+    "36": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "31": {
+    "37": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "32": {
+    "38": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -39,7 +39,6 @@
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2BertProcessor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json

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