zhangwei13
|
6a854390b4
|
add fitz_preprocess as default preprocess for image parser to align with demo
|
2025-08-11 09:44:05 +08:00 |
|
zhangwei13
|
af3a52fa32
|
add fitz_preprocess as default preprocess for image parser to align with demo
|
2025-08-11 09:20:44 +08:00 |
|
zhangwei13
|
dcd3256cc7
|
fix clean text bug
|
2025-08-07 16:22:23 +08:00 |
|
Doge2077
|
3e9c068fc3
|
fix:image base64 std-format.
|
2025-08-07 10:52:18 +08:00 |
|
Qing Yan
|
6a5e2ba95c
|
Merge pull request #33 from yjmm10/master
support infer with transformer
|
2025-08-05 21:19:48 +08:00 |
|
openmartin
|
37b62d9b7c
|
Update parser.py open file with encoding to support windows
|
2025-08-05 15:12:02 +08:00 |
|
liferecords
|
2a7d5e1f5a
|
support infer with transformers
add `--use_hf true` to use transformers,but the speed is very slower than vllm
|
2025-08-05 14:18:02 +08:00 |
|
zhangwei13
|
ae0ca3a8be
|
udpate wechat, fix some little bugs
|
2025-08-05 11:34:53 +08:00 |
|
zhangwei13
|
be77dff22c
|
dots.ocr release
|
2025-07-30 19:12:56 +08:00 |
|