tencent / HunyuanOCR

🎯 Demo | 📥 Model Download | 📄 Technical Report | 🌟 Github

📖 Introduction

HunyuanOCR stands as a leading end-to-end OCR expert VLM powered by Hunyuan's native multimodal architecture. With a remarkably lightweight 1B parameter design, it has achieved multiple state-of-the-art benchmarks across the industry. The model demonstrates mastery in complex multilingual document parsing while excelling in practical applications including text spotting, open-field information extraction, video subtitle extraction, and photo translation .

🚀 Quick Start with Transformers

Installation

pip install git+https://github.com/huggingface/transformers@82a06db03535c49aa987719ed0746a76093b1ec4

Note : We will merge it into the Transformers main branch later.

Model Inference

from transformers import AutoProcessor
from transformers import HunYuanVLForConditionalGeneration
from PIL import Image
import torch

model_name_or_path = "tencent/HunyuanOCR"
processor = AutoProcessor.from_pretrained(model_name_or_path, use_fast=False)
img_path = "path/to/your/image.jpg"
image_inputs = Image.open(img_path)
messages1 = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": img_path},
            {"type": "text", "text": (
                "Extract all information from the main body of the document image "
                "and represent it in markdown format, ignoring headers and footers. "
                "Tables should be expressed in HTML format, formulas in the document "
                "should be represented using LaTeX format, and the parsing should be "
                "organized according to the reading order."
            )},
        ],
    }
]
messages = [messages1]
texts = [
    processor.apply_chat_template(msg, tokenize=False, add_generation_prompt=True)
    for msg in messages
]
inputs = processor(
    text=texts,
    images=image_inputs,
    padding=True,
    return_tensors="pt",
)
model = HunYuanVLForConditionalGeneration.from_pretrained(
    model_name_or_path,
    attn_implementation="eager",
    dtype=torch.bfloat16,
    device_map="auto"
)
with torch.no_grad():
    device = next(model.parameters()).device
    inputs = inputs.to(device)
    generated_ids = model.generate(**inputs, max_new_tokens=16384, do_sample=False)
if "input_ids" in inputs:
    input_ids = inputs.input_ids
else:
    print("inputs: # fallback", inputs)
    input_ids = inputs.inputs
generated_ids_trimmed = [
    out_ids[len(in_ids):] for in_ids, out_ids in zip(input_ids, generated_ids)
]
output_texts = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_texts)

🚀 Quick Start with vLLM

Installation

pip install vllm --extra-index-url https://wheels.vllm.ai/nightly

Model Inference

from vllm import LLM, SamplingParams
from PIL import Image
from transformers import AutoProcessor

model_path = "tencent/HunyuanOCR"
llm = LLM(model=model_path)
processor = AutoProcessor.from_pretrained(model_path)
sampling_params = SamplingParams(temperature=0.0, max_tokens=16384)

img_path = "/path/to/image.jpg"
img = Image.open(img_path)
messages = [
    {"role": "user", "content": [
        {"type": "image", "image": img_path},
        {"type": "text", "text": "Detect and recognize text in the image, and output the text coordinates in a formatted manner."}
    ]}
]
prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = {"prompt": prompt, "multi_modal_data": {"image": [img]}}
output = llm.generate([inputs], sampling_params)[0]
print(output.outputs[0].text)

💬 Application-oriented Prompts

📚 Citation

@misc{hunyuanocr2025, title={HunyuanOCR Technical Report}, author={Tencent Hunyuan Vision Team}, year={2025}, publisher={GitHub}, journal={GitHub repository}, howpublished={\url{ https://github.com/Tencent-Hunyuan/HunyuanOCR}} }

🙏 Acknowledgements

We would like to thank PaddleOCR , MinerU , MonkeyOCR , DeepSeek-OCR , dots.ocr for their valuable models and ideas. We also appreciate the benchmarks: OminiDocBench , OCRBench , DoTA .

Special thanks to vLLM Community for Day-0 inference support.