quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4", # Or "fp4"
    bnb_4bit_compute_dtype="float16",
    bnb_4bit_use_double_quant=True
)
base_model = Qwen2AudioForConditionalGeneration.from_pretrained("Qwen/Qwen2-Audio-7B", quantization_config=quantization_config,
                                                        device_map="auto", trust_remote_code=True)
lora_model = PeftModel.from_pretrained(temp, "KaileyM/qwen2audio-lora-music-descriptor", device_map="auto")

processor = AutoProcessor.from_pretrained("Qwen/Qwen2-Audio-7B" ,trust_remote_code=True)

def describe_music(audio, model):
  prompt = "<|audio_bos|><|AUDIO|><|audio_eos|>Describe the music thoroughly:"

  inputs = processor(text=prompt, audio=audio, sampling_rate=16000, padding=False, return_tensors="pt")

  inputs = {k: v.to(model.device) for k, v in inputs.items()}

  with torch.no_grad():
    generated_ids = model.generate(**inputs, max_new_tokens=128)

  # remove prompt tokens from generation
  generated_ids = generated_ids[:, inputs["input_ids"].size(1):]

  description = processor.decode(
    generated_ids, skip_special_tokens=True)
  
  return description