from io import BytesIO
from urllib.request import urlopen
import librosa
from transformers import Qwen2AudioForConditionalGeneration, AutoProcessor
from transformers import BitsAndBytesConfig
import torch

Configure 4-bit quantization

quantization_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_compute_dtype=torch.float16,
bnb_4bit_quant_type="nf4",
bnb_4bit_use_double_quant=True,
)

processor = AutoProcessor.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct")
model = Qwen2AudioForConditionalGeneration.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct", device_map="auto",quantization_config=quantization_config)