I have tried all the possible combination of various Transformer models across diferrent version but I still end up with this issue.
Have you guys tried running this inference code on huggingface?

pip install transformers peft librosa
import transformers
import numpy as np
import librosa

pipe = transformers.pipeline(model='fixie-ai/ultravox-v0_6-gemma-3-27b', trust_remote_code=True)

path = "" # TODO: pass the audio here
audio, sr = librosa.load(path, sr=16000)

turns = [
{
"role": "system",
"content": "You are a friendly and helpful character. You love to answer questions for people."
},
]
pipe({'audio': audio, 'turns': turns, 'sampling_rate': sr}, max_new_tokens=30)