import soundfile as sf
import torch
from transformers import Qwen2_5OmniModel, Qwen2_5OmniProcessor
from qwen_omni_utils import process_mm_info


'''
FORCE_QWENVL_VIDEO_READER=decord # 强制使用decord 后端
'''
# default: Load the model on the available device(s)
model = Qwen2_5OmniModel.from_pretrained("Qwen/Qwen2.5-Omni-7B", torch_dtype=torch.bfloat16, device_map="auto", attn_implementation="flash_attention_2")

# We recommend enabling flash_attention_2 for better acceleration and memory saving.
# model = Qwen2_5OmniModel.from_pretrained(
#     "Qwen/Qwen2.5-Omni-7B",
#     torch_dtype="auto",
#     device_map="auto",
#     attn_implementation="flash_attention_2",
# )

processor = Qwen2_5OmniProcessor.from_pretrained("Qwen/Qwen2.5-Omni-7B")

conversation = [
    {
        "role": "system",
        "content": "You are Qwen, a virtual human developed by the Qwen Team, Alibaba Group, capable of perceiving auditory and visual inputs, as well as generating text and speech.",
    },
    {
        "role": "user",
        "content": [
            {"type": "video", "video": "./draw.mp4"},
        ],
    },
]

# Preparation for inference
text = processor.apply_chat_template(conversation, add_generation_prompt=True, tokenize=False)
audios, images, videos = process_mm_info(conversation, use_audio_in_video=True)
inputs = processor(text=text, audios=audios, images=images, videos=videos, return_tensors="pt", padding=True)
inputs = inputs.to(model.device).to(model.dtype)

# Inference: Generation of the output text and audio
text_ids, audio = model.generate(**inputs, use_audio_in_video=True)
text = processor.batch_decode(text_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)
print(text)
sf.write(
    "output.wav",
    audio.reshape(-1).detach().cpu().numpy(),
    samplerate=24000,
)