Baidupaddleocr
baidu/paddleocrModel for table extraction that receives an image as input, runs OCR on the image, and returns the text within the image and its bounding boxes.
inspect — the catalog entry
{
"name": "paddleocr",
"publisher": "baidu",
"labels": [
"Optical Character Recognition",
"B200",
"Table Extraction",
"Optical Character Detection",
"H100 NVL",
"A100 PG509 200",
"run-on-rtx",
"extraction",
"nemo retriever",
"A100 SXM4 80GB",
"L4",
"data ingestion",
"Download Available",
"L40S",
"A10G",
"H100 80GB HBM3"
],
"attributes": {
"AVAILABLE": "true",
"last_month_download_count": "13129",
"lastMonthApiInvocationCount": "3244",
"lastMonthDownloadCount": "13377",
"logo": "https://assets.ngc.nvidia.com/products/api-catalog/images/paddleocr.jpg",
"PREVIEW": "false",
"last_month_api_invocation_count": "9445"
},
"id": "baidu/paddleocr",
"description": "Model for table extraction that receives an image as input, runs OCR on the image, and returns the text within the image and its bounding boxes.",
"context_length": null
}