fix: handle torch.dtype serialization in config classes

Fixes #199 - Object of type dtype is not JSON serializable

When loading models with torch_dtype as a torch.dtype object (e.g.,
torch.bfloat16), transformers would fail to serialize the config to
JSON for logging purposes, raising TypeError.

This fix:
- Adds _convert_dtype_to_string() helper function to convert torch.dtype
  objects to their string representation (e.g., 'bfloat16')
- Overrides to_dict() method in VibeVoiceConfig, VibeVoiceASRConfig,
  and VibeVoiceStreamingConfig to apply this conversion

The fix is backward compatible - string dtype values and None values
continue to work as expected.

vibevoice/modular/configuration_vibevoice_streaming.py

@@ -1,11 +1,12 @@
 """ VibeVoice Streaming model configuration"""
 
+import torch
 from transformers.configuration_utils import PretrainedConfig 
 from transformers.utils import logging
 
 from transformers.models.qwen2.configuration_qwen2 import Qwen2Config
 
-from .configuration_vibevoice import VibeVoiceAcousticTokenizerConfig, VibeVoiceDiffusionHeadConfig
+from .configuration_vibevoice import VibeVoiceAcousticTokenizerConfig, VibeVoiceDiffusionHeadConfig, _convert_dtype_to_string
 
 logger = logging.get_logger(__name__)
 
@@ -80,6 +81,15 @@ class VibeVoiceStreamingConfig(PretrainedConfig):
 
         super().__init__(**kwargs)
 
+    def to_dict(self):
+        """
+        Override to_dict to handle torch.dtype serialization.
+        
+        Fixes: https://github.com/microsoft/VibeVoice/issues/199
+        """
+        output = super().to_dict()
+        return _convert_dtype_to_string(output)
+
 __all__ = [
     "VibeVoiceStreamingConfig"
 ]