Unlimited-OCR · Issues· 78 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #81
Non-CUDA inference: CPU works after removing hardcoded .cuda(); MPS (Apple Silicon) crashes mid-generation
Updated Sep 8, 2026 - #69
Your project is on StackMap — a curated map of the AI stack
Updated Sep 6, 2026 - #97
[Feature Request] Add Agent skill/tool integration interface for OCR capability
Updated Sep 1, 2026 - #82
Output texts keeps on repeating infinitely [Tried with llama.cpp server running on ubuntu 22.04]
Updated Aug 23, 2026 - #18
Apple Silicon (MPS): empty output — masked_scatter with a broadcast mask scatters incorrectly on Metal
Updated Aug 17, 2026 - #95
ArabicOCR
Updated Aug 12, 2026 - #94
Is the source code for the Hugging Face Spaces web demo available?
Updated Aug 12, 2026 - #93
模型推理部署
Updated Aug 10, 2026 - #90
Hebrew text: model outputs a hallucinated token while Latin text on the same image is read correctly — is Hebrew supported?
Updated Aug 4, 2026 - #89
Enhancement / Discussion: Benchmark and Support for Arabic Language Parsing via arafix
Updated Aug 3, 2026 - #88
dokOSR
Updated Aug 2, 2026 - #66
OmniDocBench v1.6 text EditDist: we measure 0.087 vs ~0.042 implied by the reported Overall — CDM/TEDS at parity; requesting eval methodology
Updated Aug 1, 2026 - #87
Herramientas
Updated Aug 1, 2026 - #3
Language Support
Updated Jul 29, 2026 - #84
Patent's ST.25 listings become tables and digit-changing generation loops in vLLM
Updated Jul 26, 2026