Print duplicate characters

2026-09-10 11:50:20 +08:00 · 2022-02-25 10:48:03 +01:00
parent 3de9f38d16
commit 87bf940676
1 changed files with 1 additions and 1 deletions
@@ -206,7 +206,7 @@ class BaseCharacters:
        if self.is_unique:
            assert (
                len(self.vocab) == len(self._char_to_id) == len(self._id_to_char)
-            ), f" [!] There are duplicate characters in the character set."
+            ), f" [!] There are duplicate characters in the character set. {set([x for x in self.vocab if self.vocab.count(x) > 1])}"

    def char_to_id(self, char: str) -> int:
        return self._char_to_id[char]