diff --git a/vocab.json b/vocab.json
new file mode 100644
index 0000000..29389db
--- /dev/null
+++ b/vocab.json
@@ -0,0 +1,34 @@
+{
+    "<pad>": 0,
+    "<s>": 1,
+    "</s>": 2,
+    "<unk>": 3,
+    "|": 4,
+    "E": 5,
+    "T": 6,
+    "A": 7,
+    "O": 8,
+    "N": 9,
+    "I": 10,
+    "H": 11,
+    "S": 12,
+    "R": 13,
+    "D": 14,
+    "L": 15,
+    "U": 16,
+    "M": 17,
+    "W": 18,
+    "C": 19,
+    "F": 20,
+    "G": 21,
+    "Y": 22,
+    "P": 23,
+    "B": 24,
+    "V": 25,
+    "K": 26,
+    "'": 27,
+    "X": 28,
+    "J": 29,
+    "Q": 30,
+    "Z": 31
+}
\ No newline at end of file