Qwen2.5-Omni

pip uninstall transformers
pip install git+https://github.com/huggingface/transformers@v4.51.3-Qwen2.5-Omni-preview
pip install accelerate

KeyError: 'qwen2_5_omni'

# It's highly recommended to use `[decord]` feature for faster video loading.
pip install qwen-omni-utils[decord] -U

import soundfile as sf

from transformers import Qwen2_5OmniForConditionalGeneration, Qwen2_5OmniProcessor
from qwen_omni_utils import process_mm_info

# default: Load the model on the available device(s)
model = Qwen2_5OmniForConditionalGeneration.from_pretrained("Qwen/Qwen2.5-Omni-7B", torch_dtype="auto", device_map="auto")

# We recommend enabling flash_attention_2 for better acceleration and memory saving.
# model = Qwen2_5OmniForConditionalGeneration.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": [
            {"type": "text", "text": "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": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2.5-Omni/draw.mp4"},
        ],
    },
]

# set use audio in video
USE_AUDIO_IN_VIDEO = True

# 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=USE_AUDIO_IN_VIDEO)
inputs = processor(text=text, audio=audios, images=images, videos=videos, return_tensors="pt", padding=True, use_audio_in_video=USE_AUDIO_IN_VIDEO)
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=USE_AUDIO_IN_VIDEO)

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,
)

# Sample messages for batch inference

# Conversation with video only
conversation1 = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "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": "/path/to/video.mp4"},
        ]
    }
]

# Conversation with audio only
conversation2 = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "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": "audio", "audio": "/path/to/audio.wav"},
        ]
    }
]

# Conversation with pure text
conversation3 = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "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": "who are you?"
    }
]


# Conversation with mixed media
conversation4 = [
    {
        "role": "system",
        "content": [
            {"type": "text", "text": "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": "image", "image": "/path/to/image.jpg"},
            {"type": "video", "video": "/path/to/video.mp4"},
            {"type": "audio", "audio": "/path/to/audio.wav"},
            {"type": "text", "text": "What are the elements can you see and hear in these medias?"},
        ],
    }
]

# Combine messages for batch processing
conversations = [conversation1, conversation2, conversation3, conversation4]

# set use audio in video
USE_AUDIO_IN_VIDEO = True

# Preparation for batch inference
text = processor.apply_chat_template(conversations, add_generation_prompt=True, tokenize=False)
audios, images, videos = process_mm_info(conversations, use_audio_in_video=USE_AUDIO_IN_VIDEO)

inputs = processor(text=text, audio=audios, images=images, videos=videos, return_tensors="pt", padding=True, use_audio_in_video=USE_AUDIO_IN_VIDEO)
inputs = inputs.to(model.device).to(model.dtype)

# Batch Inference
text_ids = model.generate(**inputs, use_audio_in_video=USE_AUDIO_IN_VIDEO, return_audio=False)
text = processor.batch_decode(text_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)
print(text)

{
    "role": "system",
    "content": [
        {"type": "text", "text": "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."}
    ],
}

# first place, in data preprocessing
audios, images, videos = process_mm_info(conversations, use_audio_in_video=True)

# second place, in model processor
inputs = processor(text=text, audio=audios, images=images, videos=videos, return_tensors="pt", 
                   padding=True, use_audio_in_video=True)

#  third place, in model inference
text_ids, audio = model.generate(**inputs, use_audio_in_video=True)

model = Qwen2_5OmniForConditionalGeneration.from_pretrained(
    "Qwen/Qwen2.5-Omni-7B",
    torch_dtype="auto",
    device_map="auto"
)
model.disable_talker()

model = Qwen2_5OmniForConditionalGeneration.from_pretrained(
    "Qwen/Qwen2.5-Omni-7B",
    torch_dtype="auto",
    device_map="auto"
)
...
text_ids = model.generate(**inputs, return_audio=False)

text_ids, audio = model.generate(**inputs, speaker="Chelsie")

text_ids, audio = model.generate(**inputs, speaker="Ethan")

pip install -U flash-attn --no-build-isolation

from transformers import Qwen2_5OmniForConditionalGeneration

model = Qwen2_5OmniForConditionalGeneration.from_pretrained(
    "Qwen/Qwen2.5-Omni-7B",
    device_map="auto",
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
)

@article{Qwen2.5-Omni,
  title={Qwen2.5-Omni Technical Report},
  author={Jin Xu, Zhifang Guo, Jinzheng He, Hangrui Hu, Ting He, Shuai Bai, Keqin Chen, Jialin Wang, Yang Fan, Kai Dang, Bin Zhang, Xiong Wang, Yunfei Chu, Junyang Lin},
  journal={arXiv preprint arXiv:2503.20215},
  year={2025}
}