Update README.md
Browse files
README.md
CHANGED
|
@@ -28,8 +28,6 @@ library_name: transformers
|
|
| 28 |
## 📖 Introduction
|
| 29 |
**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**.
|
| 30 |
|
| 31 |
-
Built on Tencent's Hunyuan technology, this versatile model delivers exceptional performance through end-to-end architecture design and single-pass inference. It significantly simplifies deployment while maintaining competitive performance against both established cascade systems and commercial APIs.
|
| 32 |
-
|
| 33 |
|
| 34 |
## 🚀 Quick Start with Transformers
|
| 35 |
|
|
|
|
| 28 |
## 📖 Introduction
|
| 29 |
**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**.
|
| 30 |
|
|
|
|
|
|
|
| 31 |
|
| 32 |
## 🚀 Quick Start with Transformers
|
| 33 |
|