cudanexus/ocr-surya 🖼️❓🔢📝 → ❓

▶️ 6.5K runs 📅 Feb 2024 ⚙️ Cog 0.9.4 🔗 GitHub ⚖️ License
image-to-text multilingual-ocr ocr

About

Surya is a document OCR toolkit that does:

Example Output

Output

Performance Metrics

7.99s Prediction Time
254.47s Total Time
All Input Parameters
{
  "image": "https://replicate.delivery/pbxt/KU3ZDwmFqwo7tsfY5m8OsN0XDJLqk2lvgSKOT5s7HFZOqkNq/D5300-1.jpg",
  "action": "Run OCR",
  "page_number": 1,
  "languages_input": "English",
  "languages_choices": "English"
}
Input Parameters
image (required) Type: string
Upload PDF or Image
action Default: Run Text Detection
Action
page_number Type: integerDefault: 1
Page Number
languages_input Type: stringDefault: English
Languages (comma-separated list)
languages_choices Default: English
Languages
Output Schema
image Type: stringFormat: uri
Image
Status Type: string
text_file Type: stringFormat: uri
Text File
Example Execution Logs
Detecting bboxes:   0%|          | 0/1 [00:00<?, ?it/s]
Detecting bboxes: 100%|██████████| 1/1 [00:01<00:00,  1.17s/it]
Detecting bboxes: 100%|██████████| 1/1 [00:01<00:00,  1.17s/it]
Recognizing Text:   0%|          | 0/1 [00:00<?, ?it/s]/root/.pyenv/versions/3.11.8/lib/python3.11/site-packages/transformers/generation/utils.py:1518: UserWarning: You have modified the pretrained model configuration to control generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use and modify the model generation configuration (see https://huggingface.co/docs/transformers/generation_strategies#default-text-generation-configuration )
warnings.warn(
Recognizing Text: 100%|██████████| 1/1 [00:04<00:00,  4.77s/it]
Recognizing Text: 100%|██████████| 1/1 [00:04<00:00,  4.77s/it]
<tempfile._TemporaryFileWrapper object at 0x7dbfd272e190> /tmp/tmpup9030rb.jpg
Version Details
Version ID
7ab5bedee2cd1f0c82b2df6718d19bf0b473f738f9db062f122e47e1467f96ce
Version Created
February 28, 2024
Run on Replicate →