Issues
- 1
Report an error: RuntimeWarning: invalid value encountered in cast aff_img = Image.fromarray((affinity_map * 255).astype(np.uint8))
#287 opened by potatoo0000 - 2
OCR_ENGINE=None Doesn't work
#256 opened by svmrw - 0
batch processing stuck
#286 opened by jonabert - 0
pdf to quarto markdown
#285 opened by horhenani - 0
- 1
Feature request: URL extraction
#283 opened by ShakirAkbari - 1
- 0
Feature Request
#282 opened by kssextro - 8
IMPORTANT:Total elapsed time of loading model is 3.1 minutes, super slow, is it normal?
#249 opened by ckgithub2019 - 5
PermissionError: [Errno 13] Permission denied: 'C:\\Users\\schor\\AppData\\Local\\Temp\\tmpoaply4el.pdf'
#267 opened by Schorakbi - 0
module 'torch.nn' has no attribute 'RMSNorm'
#281 opened by robertio - 0
- 0
IndexError: list index out of range (New)
#279 opened by wooemans - 1
Absolut Gobboly Goo Output Markdown
#277 opened by lucaspeyrin - 0
option to output markdown to stdout?
#275 opened by daboe01 - 5
Chang default output setting
#271 opened by yibie - 0
Broken superscripts (references to bibliography items, footnotes, author affiliations, etc.)
#274 opened by XZF0 - 4
- 0
finetune issue
#273 opened by Frank-Zeng - 0
marker识别公式能力是不是很差啊
#272 opened by orcharddd1990 - 2
- 1
- 0
ImportError: Failed to load PyTorch C extensions
#268 opened by mctouch - 2
- 0
- 1
Update minimal required Python to 3.10
#264 opened by rmast - 3
- 0
Improving OCR through higher image DPI?
#262 opened by kkarski - 3
CONFUSING! About Optional: OCRMyPDF
#248 opened by ckgithub2019 - 0
Is there any way to enhance the bibliography?
#260 opened by flight505 - 0
Improve cold boot time
#259 opened by frankbaele - 1
is it possible to update build with numpy < 2
#258 opened by flight505 - 1
how to use extra settings , like OCR_ALL_PAGES ?
#238 opened by FanWan - 4
TypeError: Invalid input type 'PdfDocument'
#235 opened by Liu-XinYuan - 1
Help!settings is not Take effect
#254 opened by caixiongjiang - 0
suggest to json.dumps with `ensure_ascii=False`
#253 opened by Honglei-Cong - 1
ImportError: cannot import name 'segformer' from 'surya.model.detection' (unknown location)
#247 opened by Beaverfffan - 0
upload image to s3 automatically
#251 opened by liqiankun1111 - 0
Issues about "OCR_ALL_PAGES" and "num_chunks"
#250 opened by ckgithub2019 - 0
subprocess.CalledProcessError: Command 'marker /data/mypdf/data/tmp /data/mypdf/tmp_pdf --workers 2 --max 2 ' died with <Signals.SIGSEGV: 11>.
#246 opened by 0x01111 - 0
Issue Parsing Hand Written Material
#244 opened by kkailaasa - 0
Token indices sequence length is longer than the specified maximum sequence length for this model (557>384)
#243 opened by TSECP - 1
- 0
- 1
Memory Leak when Converting Long PDFs to Markdown
#240 opened by pigPEQ - 0
Cannot convert inline latex
#239 opened by Barmaid1076 - 0
One general question.
#236 opened by AbhayMishraVK - 0
How can I get the text part and table part separately?
#233 opened by taichiwym - 0
Errors when trying to run
#232 opened by MrUnknown789556 - 0
Detected 50 pdf files, but only parsed 44 files
#231 opened by chosenduke