Fix AttributeError: 'NoneType' object has no attribute 'tokenizer'

Steps to reproduce the issue:
```
import transformers
import librosa

model_name = "fixie-ai/ultravox-v0_4-mistral_nemo"
tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)

pipe = transformers.pipeline(model=model_name, tokenizer=tokenizer, trust_remote_code=True)

path = "foo.ogg"
audio, sr = librosa.load(path, sr=16000)

turns = [
{"role": "user", "content": "Explain what is happening in the audio"}
]

pipe({'audio': audio, 'turns': turns, 'sampling_rate': sr}, max_new_tokens=30)
```

ultravox_pipeline.py

@@ -33,14 +33,14 @@ class UltravoxPipeline(transformers.Pipeline):
                 model.config.audio_model_id or model.config.audio_config._name_or_path
             )
 
+        super().__init__(model=model, tokenizer=tokenizer, **kwargs)
+        
         self.processor = UltravoxProcessor(
             audio_processor=audio_processor,
             tokenizer=tokenizer,
             stack_factor=model.config.stack_factor,
         )
 
-        super().__init__(model=model, tokenizer=tokenizer, **kwargs)
-
     def _sanitize_parameters(self, **kwargs):
         generation_keys = ["temperature", "max_new_tokens", "repetition_penalty"]
         generation_kwargs = {k: kwargs[k] for k in kwargs if k in generation_keys}