 myhloli
|
9951a17026
style(pdf_parse_union_core_v2): remove unnecessary spaces and improve code formatting- Remove extra space in conditional statement for character spacing logic
|
10 months ago |
|
myhloli
|
7c5cdcd4d7
refactor(pdf_parse): improve character spacing handling in PDF text extraction
|
10 months ago |
|
myhloli
|
2684e7753b
fix(npu): correct module name for NPU operations
|
10 months ago |
|
myhloli
|
50f4841716
refactor(device): optimize memory cleaning and device selection
|
11 months ago |
|
myhloli
|
7990e7dfbb
feat(model): add npu support and optimize table model
|
11 months ago |
|
myhloli
|
0a468eca6e
feat(llm_aided): add title optimization feature
|
11 months ago |
|
Xiaomeng Zhao
|
da3257a631
Merge pull request #1352 from myhloli/add-llm-aided
|
11 months ago |
|
myhloli
|
c660fdc8f0
feat(llm): add LLM-aided formula and text correction
|
11 months ago |
|
myhloli
|
15e876677d
refactor(pre_proc): improve character overlap handling in spans
|
11 months ago |
|
myhloli
|
2f4d4b0c80
feat(pre_proc): add function to remove overlapping characters in spans
|
11 months ago |
 pangguosheng
|
51b8c57df2
fix: skip the char corresponding to invalid bounding boxes
|
11 months ago |
|
myhloli
|
9e4ebea939
refactor(magic_pdf): remove YOLO_VERBOSE setting and update YOLOv8 prediction verbosity
|
11 months ago |
|
myhloli
|
c638fc5d1f
fix(pdf): improve ligature handling and text extraction
|
11 months ago |
|
myhloli
|
9efc35ecaa
refactor(magic_pdf): remove unused import in pdf_parse_union_core_v2.py
|
11 months ago |
|
Xiaomeng Zhao
|
fa113b5750
Merge pull request #1178 from icecraft/refactor/add_user_api
|
11 months ago |
|
myhloli
|
012a46e07d
refactor(magic-pdf): optimize model initialization and concurrency control
|
11 months ago |
|
myhloli
|
47a83d28f5
refactor(ocr): replace AtomModelSingleton with ocr_model_init for OCR model instantiation
|
11 months ago |
|
myhloli
|
f2a92d5782
refactor(model): implement thread-safe OCR model initialization
|
11 months ago |
|
myhloli
|
a1744b770f
refactor(magic_pdf): remove unused threading lock and model initialization code
|
11 months ago |
|
myhloli
|
30220233ab
refactor(magic_pdf): replace AtomModelSingleton with ocr_model_init for OCR model instantiation
|
11 months ago |
 xu rui
|
f6bd47de6a
docs: add dataset method description
|
11 months ago |
|
icecraft
|
4a82d6a07a
feat: add function definitions
|
1 year ago |
|
icecraft
|
a3a720ea87
refactor: isolate inference and pipeline
|
1 year ago |
|
myhloli
|
d4345b6e39
refactor(pdf_parse): adjust character-axis alignment algorithm
|
1 year ago |
|
myhloli
|
949d0867fb
feat(pdf_parse): add line start flag detection and optimize line stop flag logic
|
1 year ago |
|
myhloli
|
ac88815620
refactor(pdf_check): improve character detection using PyMuPDF
|
1 year ago |
|
myhloli
|
88c0854a65
refactor(ocr): improve text processing and span handling
|
1 year ago |
|
myhloli
|
37da8c44c4
feat(pdf_parse): filter out skewed text lines
|
1 year ago |
|
myhloli
|
08392d63a0
fix(Hybrid OCR):Enable Hybrid OCR for Empty Spans That Contain a Certain Number of Placeholders but No Actual Text
|
1 year ago |
|
myhloli
|
1d2eb70aa0
refactor(pdf_parse_union_core_v2): optimize page processing time logging
|
1 year ago |
