fix: use hasattr for BatchEncoding compatibility

tokenization_voxcpm2.py

@@ -57,7 +57,7 @@ class VoxCPM2Tokenizer(LlamaTokenizerFast):
 
     def __call__(self, text, *args, **kwargs):
         result = super().__call__(text, *args, **kwargs)
-        if isinstance(result, dict) and "input_ids" in result:
+        if hasattr(result, "input_ids"):
             ids = result["input_ids"]
             if isinstance(ids, list) and ids and isinstance(ids[0], list):
                 result["input_ids"] = [self._expand_ids(x) for x in ids]
@@ -65,7 +65,7 @@ class VoxCPM2Tokenizer(LlamaTokenizerFast):
                     result["attention_mask"] = [
                         [1] * len(x) for x in result["input_ids"]
                     ]
-            else:
+            elif isinstance(ids, list):
                 result["input_ids"] = self._expand_ids(ids)
                 if "attention_mask" in result:
                     result["attention_mask"] = [1] * len(result["input_ids"])