File size: 1,574 Bytes
25e3edb 5f92780 25e3edb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
---
pipeline_tag: image-text-to-text
library_name: transformers
language:
- multilingual
tags:
- got
- vision-language
- ocr2.0
- custom_code
license: apache-2.0
---
## Usage
Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.10：
```
torch==2.0.1
torchvision==0.15.2
transformers==4.37.2
tiktoken==0.6.0
verovio==4.3.1
accelerate==0.28.0
```
```python
from transformers import AutoModel, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('Cherryblade29/ocr', trust_remote_code=True)
model = AutoModel.from_pretrained('Cherryblade29/ocr', trust_remote_code=True, low_cpu_mem_usage=True, device_map='cuda', use_safetensors=True, pad_token_id=tokenizer.eos_token_id)
model = model.eval().cuda()
# input your test image
image_file = 'xxx.jpg'
# plain texts OCR
res = model.chat(tokenizer, image_file, ocr_type='ocr')
# format texts OCR:
# res = model.chat(tokenizer, image_file, ocr_type='format')
# fine-grained OCR:
# res = model.chat(tokenizer, image_file, ocr_type='ocr', ocr_box='')
# res = model.chat(tokenizer, image_file, ocr_type='format', ocr_box='')
# res = model.chat(tokenizer, image_file, ocr_type='ocr', ocr_color='')
# res = model.chat(tokenizer, image_file, ocr_type='format', ocr_color='')
# multi-crop OCR:
# res = model.chat_crop(tokenizer, image_file, ocr_type='ocr')
# res = model.chat_crop(tokenizer, image_file, ocr_type='format')
# render the formatted OCR results:
# res = model.chat(tokenizer, image_file, ocr_type='format', render=True, save_render_file = './demo.html')
print(res)
```
|