Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
-base_model: facebook/wav2vec2-large-xlsr-53
 tags:
 - generated_from_trainer
+base_model: facebook/wav2vec2-large-xlsr-53
 model-index:
 - name: wav2vec2-large-vn-lang-test-3
   results: []

vocab.json

@@ -1,53 +1,53 @@
 {
   "[PAD]": 50,
   "[UNK]": 49,
-  "a": 30,
-  "b": 14,
-  "c": 1,
-  "e": 39,
+  "a": 21,
+  "b": 47,
+  "c": 11,
+  "e": 5,
   "g": 29,
-  "h": 23,
-  "i": 10,
-  "k": 41,
-  "l": 31,
-  "m": 4,
-  "n": 3,
-  "o": 36,
-  "p": 38,
-  "q": 5,
-  "r": 8,
-  "s": 45,
-  "t": 33,
-  "u": 2,
-  "v": 37,
-  "x": 13,
-  "y": 47,
-  "|": 48,
-  "à": 19,
-  "á": 22,
-  "ã": 44,
-  "ê": 46,
-  "ó": 35,
-  "ô": 20,
-  "ú": 11,
-  "đ": 7,
-  "ũ": 9,
-  "ơ": 42,
-  "ư": 21,
-  "ạ": 25,
-  "ả": 28,
-  "ầ": 16,
-  "ậ": 32,
-  "ắ": 26,
-  "ẹ": 6,
-  "ẽ": 40,
-  "ế": 17,
-  "ề": 27,
-  "ể": 0,
-  "ọ": 12,
-  "ố": 34,
-  "ỗ": 18,
-  "ớ": 24,
-  "ờ": 15,
-  "ợ": 43
+  "h": 44,
+  "i": 32,
+  "k": 19,
+  "l": 41,
+  "m": 42,
+  "n": 10,
+  "o": 20,
+  "p": 25,
+  "q": 31,
+  "r": 12,
+  "s": 43,
+  "t": 39,
+  "u": 37,
+  "v": 45,
+  "x": 9,
+  "y": 3,
+  "|": 14,
+  "à": 23,
+  "á": 34,
+  "ã": 26,
+  "ê": 22,
+  "ó": 0,
+  "ô": 8,
+  "ú": 4,
+  "đ": 28,
+  "ũ": 48,
+  "ơ": 16,
+  "ư": 18,
+  "ạ": 15,
+  "ả": 30,
+  "ầ": 40,
+  "ậ": 33,
+  "ắ": 38,
+  "ẹ": 7,
+  "ẽ": 36,
+  "ế": 2,
+  "ề": 1,
+  "ể": 17,
+  "ọ": 35,
+  "ố": 13,
+  "ỗ": 46,
+  "ớ": 6,
+  "ờ": 24,
+  "ợ": 27
 }