Bump marker version to 1.2.0

xiaoyao9184 · xiaoyao9184 · commit 49560f38b070 · 2025-01-05T17:45:19.000+08:00
diff --git a/.github/workflows/docker-image-tag-version.yml b/.github/workflows/docker-image-tag-version.yml
@@ -13,11 +13,11 @@ on:
       marker_version:
         description: marker version of pypi
         required: true
-        default: 1.1.0
+        default: 1.2.0
       streamlit_version:
         description: streamlit version of pypi
         required: true
-        default: 1.41.0
+        default: 1.41.1
 
 jobs:
   build-and-push-docker-image:
@@ -29,9 +29,9 @@ jobs:
     strategy:
       matrix:
         MARKER_VERSION:
-          - ${{ github.event.inputs.marker_version || '1.1.0' }}
+          - ${{ github.event.inputs.marker_version || '1.2.0' }}
         STREAMLIT_VERSION:
-          - ${{ github.event.inputs.streamlit_version || '1.41.0' }}
+          - ${{ github.event.inputs.streamlit_version || '1.41.1' }}
         platform:
           - linux/amd64
 
diff --git a/.vscode/launch.json b/.vscode/launch.json
@@ -35,8 +35,9 @@
                 "XDG_CACHE_HOME": "${workspaceFolder}/cache",
                 "HF_HUB_OFFLINE": "true",
                 "DETECTOR_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_det3/snapshots/467ee9ec33e6e6c5f73e57dbc1415b14032f5b95",
-                "LAYOUT_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--surya_layout0/snapshots/421ac206a400227ea714d47a405e53ce74374957",
                 "RECOGNITION_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_rec2/snapshots/6611509b2c3a32c141703ce19adc899d9d0abf41",
+                "LAYOUT_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--surya_layout/snapshots/7ac8e390226ee5fa2125dd303d827f79d31d1a1f",
+                "OCR_ERROR_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--ocr_error_detection/snapshots/c1cbda3757670fd520553eaa5197656d331de414",
                 "TABLE_REC_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_tablerec/snapshots/8bca165f81e9cee5fb382413eb23175079917d14",
                 "TEXIFY_MODEL_NAME": "${workspaceFolder}/cache/huggingface/hub/models--vikp--texify/snapshots/ce49c1fe10842e78b8be61f9e762b85ac952807d"
             },
@@ -74,8 +75,9 @@
                 "XDG_CACHE_HOME": "${workspaceFolder}/cache",
                 "HF_HUB_OFFLINE": "true",
                 "DETECTOR_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_det3/snapshots/467ee9ec33e6e6c5f73e57dbc1415b14032f5b95",
-                "LAYOUT_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--surya_layout0/snapshots/421ac206a400227ea714d47a405e53ce74374957",
                 "RECOGNITION_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_rec2/snapshots/6611509b2c3a32c141703ce19adc899d9d0abf41",
+                "LAYOUT_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--surya_layout/snapshots/7ac8e390226ee5fa2125dd303d827f79d31d1a1f",
+                "OCR_ERROR_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--ocr_error_detection/snapshots/c1cbda3757670fd520553eaa5197656d331de414",
                 "TABLE_REC_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_tablerec/snapshots/8bca165f81e9cee5fb382413eb23175079917d14",
                 "TEXIFY_MODEL_NAME": "${workspaceFolder}/cache/huggingface/hub/models--vikp--texify/snapshots/ce49c1fe10842e78b8be61f9e762b85ac952807d"
             },
@@ -107,8 +109,9 @@
                 "XDG_CACHE_HOME": "${workspaceFolder}/cache",
                 "HF_HUB_OFFLINE": "true",
                 "DETECTOR_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_det3/snapshots/467ee9ec33e6e6c5f73e57dbc1415b14032f5b95",
-                "LAYOUT_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--surya_layout0/snapshots/421ac206a400227ea714d47a405e53ce74374957",
                 "RECOGNITION_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_rec2/snapshots/6611509b2c3a32c141703ce19adc899d9d0abf41",
+                "LAYOUT_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--surya_layout/snapshots/7ac8e390226ee5fa2125dd303d827f79d31d1a1f",
+                "OCR_ERROR_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--ocr_error_detection/snapshots/c1cbda3757670fd520553eaa5197656d331de414",
                 "TEXIFY_MODEL_NAME": "${workspaceFolder}/cache/huggingface/hub/models--vikp--texify/snapshots/ce49c1fe10842e78b8be61f9e762b85ac952807d",
                 "TABLE_REC_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_tablerec/snapshots/8bca165f81e9cee5fb382413eb23175079917d14",
             },
@@ -146,8 +149,9 @@
                 "XDG_CACHE_HOME": "${workspaceFolder}/cache",
                 "HF_HUB_OFFLINE": "true",
                 "DETECTOR_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_det3/snapshots/467ee9ec33e6e6c5f73e57dbc1415b14032f5b95",
-                "LAYOUT_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--surya_layout0/snapshots/421ac206a400227ea714d47a405e53ce74374957",
                 "RECOGNITION_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_rec2/snapshots/6611509b2c3a32c141703ce19adc899d9d0abf41",
+                "LAYOUT_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--surya_layout/snapshots/7ac8e390226ee5fa2125dd303d827f79d31d1a1f",
+                "OCR_ERROR_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--ocr_error_detection/snapshots/c1cbda3757670fd520553eaa5197656d331de414",
                 "TEXIFY_MODEL_NAME": "${workspaceFolder}/cache/huggingface/hub/models--vikp--texify/snapshots/ce49c1fe10842e78b8be61f9e762b85ac952807d",
                 "TABLE_REC_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_tablerec/snapshots/8bca165f81e9cee5fb382413eb23175079917d14",
             },
@@ -187,8 +191,9 @@
                 "XDG_CACHE_HOME": "${workspaceFolder}/cache",
                 "HF_HUB_OFFLINE": "true",
                 "DETECTOR_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_det3/snapshots/467ee9ec33e6e6c5f73e57dbc1415b14032f5b95",
-                "LAYOUT_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--surya_layout0/snapshots/421ac206a400227ea714d47a405e53ce74374957",
                 "RECOGNITION_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_rec2/snapshots/6611509b2c3a32c141703ce19adc899d9d0abf41",
+                "LAYOUT_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--surya_layout/snapshots/7ac8e390226ee5fa2125dd303d827f79d31d1a1f",
+                "OCR_ERROR_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--ocr_error_detection/snapshots/c1cbda3757670fd520553eaa5197656d331de414",
                 "TEXIFY_MODEL_NAME": "${workspaceFolder}/cache/huggingface/hub/models--vikp--texify/snapshots/ce49c1fe10842e78b8be61f9e762b85ac952807d",
                 "TABLE_REC_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_tablerec/snapshots/8bca165f81e9cee5fb382413eb23175079917d14",
             },
@@ -229,8 +234,9 @@
                 "XDG_CACHE_HOME": "${workspaceFolder}/cache",
                 "HF_HUB_OFFLINE": "true",
                 "DETECTOR_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_det3/snapshots/467ee9ec33e6e6c5f73e57dbc1415b14032f5b95",
-                "LAYOUT_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--surya_layout0/snapshots/421ac206a400227ea714d47a405e53ce74374957",
                 "RECOGNITION_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_rec2/snapshots/6611509b2c3a32c141703ce19adc899d9d0abf41",
+                "LAYOUT_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--surya_layout/snapshots/7ac8e390226ee5fa2125dd303d827f79d31d1a1f",
+                "OCR_ERROR_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--datalab-to--ocr_error_detection/snapshots/c1cbda3757670fd520553eaa5197656d331de414",
                 "TEXIFY_MODEL_NAME": "${workspaceFolder}/cache/huggingface/hub/models--vikp--texify/snapshots/ce49c1fe10842e78b8be61f9e762b85ac952807d",
                 "TABLE_REC_MODEL_CHECKPOINT": "${workspaceFolder}/cache/huggingface/hub/models--vikp--surya_tablerec/snapshots/8bca165f81e9cee5fb382413eb23175079917d14",
                 "METADATA_FILE": "../pdf_meta.json",
diff --git a/.vscode/tasks.json b/.vscode/tasks.json
@@ -25,9 +25,9 @@
             "command": "docker build -t xiaoyao9184/marker:master -f ./docker/build@source/dockerfile ."
         },
         {
-            "label": "docker: build 1.1.0",
+            "label": "docker: build 1.2.0",
             "type": "shell",
-            "command": "docker build -t xiaoyao9184/marker:1.1.0 -f ./docker/build@pypi/dockerfile ."
+            "command": "docker build -t xiaoyao9184/marker:1.2.0 -f ./docker/build@pypi/dockerfile ."
         },
         {
             "label": "huggingface-cli: download models",
@@ -45,7 +45,8 @@
                 "&& huggingface-cli download vikp/surya_rec2 --revision main --cache-dir ./cache/huggingface/hub",
                 "&& huggingface-cli download vikp/surya_tablerec --revision main --cache-dir ./cache/huggingface/hub",
                 "&& huggingface-cli download vikp/texify --revision main --cache-dir ./cache/huggingface/hub",
-                "&& huggingface-cli download datalab-to/surya_layout0 --revision main --cache-dir ./cache/huggingface/hub",
+                "&& huggingface-cli download datalab-to/surya_layout --revision main --cache-dir ./cache/huggingface/hub",
+                "&& huggingface-cli download datalab-to/ocr_error_detection --revision main --cache-dir ./cache/huggingface/hub",
             ]
         },
         {
diff --git a/cache/README.md b/cache/README.md
@@ -94,6 +94,58 @@ and `./cache/huggingface/hub/models--vikp--surya_tablerec` like this
 4 directories, 19 files
 ```
 
+and `./cache/huggingface/hub/models--datalab-to--surya_layout` like this
+
+
+```
+.
+├── blobs
+│   ├── 3890b5c4361d8c355b18efcbc083d80b-10
+│   ├── 5551e790c7d99f076fb8ff17b38339138e4fc543
+│   ├── 776774696986893ca5eb478899ea9d06c20435c5
+│   ├── a6344aac8c09253b3b630fb776ae94478aa0275b
+│   └── c305af17d2fcaf52c00b125a2dfabfbe16e71454
+├── refs
+│   └── main
+└── snapshots
+    └── 7ac8e390226ee5fa2125dd303d827f79d31d1a1f
+        ├── config.json -> ../../blobs/5551e790c7d99f076fb8ff17b38339138e4fc543
+        ├── model.safetensors -> ../../blobs/3890b5c4361d8c355b18efcbc083d80b-10
+        ├── preprocessor_config.json -> ../../blobs/776774696986893ca5eb478899ea9d06c20435c5
+        └── README.md -> ../../blobs/c305af17d2fcaf52c00b125a2dfabfbe16e71454
+
+5 directories, 10 files
+```
+
+and `./cache/huggingface/hub/models--datalab-to--ocr_error_detection` like this
+
+
+```
+.
+├── blobs
+│   ├── 21f54a4b56685f29358f3a8de1f5b8d827357d07
+│   ├── 9856c52ab99c8f7435bef6bf6e4c8a86a2594187
+│   ├── 9bbecc17cabbcbd3112c14d6982b51403b264bfa
+│   ├── a6344aac8c09253b3b630fb776ae94478aa0275b
+│   ├── c305af17d2fcaf52c00b125a2dfabfbe16e71454
+│   ├── cd3c57f2e967aad6a020decd1c1c41be-10
+│   ├── e837bab60a5d204e29622d127c2dafe508aa0731
+│   └── f4a46fa248690b0b2adc680e845ec8fd491eb24c
+├── refs
+│   └── main
+└── snapshots
+    └── c1cbda3757670fd520553eaa5197656d331de414
+        ├── config.json -> ../../blobs/9856c52ab99c8f7435bef6bf6e4c8a86a2594187
+        ├── model.safetensors -> ../../blobs/cd3c57f2e967aad6a020decd1c1c41be-10
+        ├── README.md -> ../../blobs/c305af17d2fcaf52c00b125a2dfabfbe16e71454
+        ├── special_tokens_map.json -> ../../blobs/9bbecc17cabbcbd3112c14d6982b51403b264bfa
+        ├── tokenizer_config.json -> ../../blobs/f4a46fa248690b0b2adc680e845ec8fd491eb24c
+        ├── tokenizer.json -> ../../blobs/21f54a4b56685f29358f3a8de1f5b8d827357d07
+        └── vocab.txt -> ../../blobs/e837bab60a5d204e29622d127c2dafe508aa0731
+
+5 directories, 16 files
+```
+
 and `./cache/huggingface/hub/models--vikp--texify` like this
 
 ```
@@ -136,7 +188,8 @@ It will use
 - `./cache/huggingface/hub/models--vikp--surya_rec2/snapshots/6611509b2c3a32c141703ce19adc899d9d0abf41`
 - `./cache/huggingface/hub/models--vikp--surya_tablerec/snapshots/8bca165f81e9cee5fb382413eb23175079917d14`
 - `./cache/huggingface/hub/models--vikp--texify/snapshots/ce49c1fe10842e78b8be61f9e762b85ac952807d`
-- `./cache/huggingface/hub/models--datalab-to--surya_layout0/snapshots/421ac206a400227ea714d47a405e53ce74374957`
+- `./cache/huggingface/hub/models--datalab-to--surya_layout/snapshots/7ac8e390226ee5fa2125dd303d827f79d31d1a1f`
+- `./cache/huggingface/hub/models--datalab-to--ocr_error_detection/snapshots/c1cbda3757670fd520553eaa5197656d331de414`
 
 For more details, refer to [up@cpu-offline/docker-compose.yml](./../docker/up@cpu-offline/docker-compose.yml).
 
@@ -158,5 +211,6 @@ huggingface-cli download vikp/surya_det3 --repo-type model --revision main --cac
 huggingface-cli download vikp/surya_rec2 --repo-type model --revision main --cache-dir ./cache/huggingface/hub
 huggingface-cli download vikp/surya_tablerec --repo-type model --revision main --cache-dir ./cache/huggingface/hub
 huggingface-cli download vikp/texify --repo-type model --revision main --cache-dir ./cache/huggingface/hub
-huggingface-cli download datalab-to/surya_layout0 --repo-type model --revision main --cache-dir ./cache/huggingface/hub
+huggingface-cli download datalab-to/surya_layout --repo-type model --revision main --cache-dir ./cache/huggingface/hub
+huggingface-cli download datalab-to/ocr_error_detection --revision main --cache-dir ./cache/huggingface/hub
 ```
diff --git a/docker/build@pypi/dockerfile b/docker/build@pypi/dockerfile
@@ -1,5 +1,5 @@
-ARG MARKER_VERSION=1.1.0
-ARG STREAMLIT_VERSION=1.41.0
+ARG MARKER_VERSION=1.2.0
+ARG STREAMLIT_VERSION=1.41.1
 ARG GRADIO_VERSION=5.8.0
 
 
@@ -33,7 +33,8 @@ RUN pip3 install --upgrade pip
 RUN pip3 install --no-cache-dir \
     marker-pdf==${MARKER_VERSION} \
     streamlit==${STREAMLIT_VERSION} \
-    gradio==${GRADIO_VERSION}
+    gradio==${GRADIO_VERSION} \
+    datasets==2.21.0
 
 # COPY --from=fonts /fonts/GoNotoCurrent-Regular.ttf /fonts/GoNotoCurrent-Regular.ttf
 # COPY --from=fonts /fonts/GoNotoCJKCore.ttf /fonts/GoNotoCJKCore.ttf
diff --git a/docker/build@source/dockerfile b/docker/build@source/dockerfile
@@ -25,8 +25,9 @@ RUN pip3 install --upgrade pip
 COPY ./marker /app
 RUN pip3 install --no-cache-dir \
     -e . \
-    streamlit==1.41.0 \
-    gradio==5.8.0
+    streamlit==1.41.1 \
+    gradio==5.8.0 \
+    datasets==2.21.0
 # The image is too large, with layers exceeding 10GB.
 # RUN pip3 install poetry
 # RUN poetry install --no-root --with dev
diff --git a/docker/up.gradio@cpu-offline/docker-compose.yml b/docker/up.gradio@cpu-offline/docker-compose.yml
@@ -2,16 +2,17 @@
 
 services:
   marker_gradio:
-    image: xiaoyao9184/marker:1.1.0
+    image: xiaoyao9184/marker:1.2.0
     container_name: marker_pdf_gradio
     working_dir: /workspace/gradio
     command: gradio gradio_app.py
     environment:
       - TORCH_DEVICE=cpu
       - HF_HUB_OFFLINE=true
       - DETECTOR_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--vikp--surya_det3/snapshots/467ee9ec33e6e6c5f73e57dbc1415b14032f5b95
-      - LAYOUT_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--datalab-to--surya_layout0/snapshots/421ac206a400227ea714d47a405e53ce74374957
       - RECOGNITION_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--vikp--surya_rec2/snapshots/6611509b2c3a32c141703ce19adc899d9d0abf41
+      - LAYOUT_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--datalab-to--surya_layout/snapshots/7ac8e390226ee5fa2125dd303d827f79d31d1a1f
+      - OCR_ERROR_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--datalab-to--ocr_error_detection/snapshots/c1cbda3757670fd520553eaa5197656d331de414
       - TABLE_REC_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--vikp--surya_tablerec/snapshots/8bca165f81e9cee5fb382413eb23175079917d14
       - TEXIFY_MODEL_NAME=/root/.cache/huggingface/hub/models--vikp--texify/snapshots/ce49c1fe10842e78b8be61f9e762b85ac952807d
     ports:
diff --git a/docker/up.gradio@gpu-offline/docker-compose.yml b/docker/up.gradio@gpu-offline/docker-compose.yml
@@ -2,16 +2,17 @@
 
 services:
   marker_gradio:
-    image: xiaoyao9184/marker:1.1.0
+    image: xiaoyao9184/marker:1.2.0
     container_name: marker_pdf_gradio
     working_dir: /workspace/gradio
     command: gradio gradio_app.py
     environment:
       - TORCH_DEVICE=cuda
       - HF_HUB_OFFLINE=true
       - DETECTOR_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--vikp--surya_det3/snapshots/467ee9ec33e6e6c5f73e57dbc1415b14032f5b95
-      - LAYOUT_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--datalab-to--surya_layout0/snapshots/421ac206a400227ea714d47a405e53ce74374957
       - RECOGNITION_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--vikp--surya_rec2/snapshots/6611509b2c3a32c141703ce19adc899d9d0abf41
+      - LAYOUT_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--datalab-to--surya_layout/snapshots/7ac8e390226ee5fa2125dd303d827f79d31d1a1f
+      - OCR_ERROR_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--datalab-to--ocr_error_detection/snapshots/c1cbda3757670fd520553eaa5197656d331de414
       - TABLE_REC_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--vikp--surya_tablerec/snapshots/8bca165f81e9cee5fb382413eb23175079917d14
       - TEXIFY_MODEL_NAME=/root/.cache/huggingface/hub/models--vikp--texify/snapshots/ce49c1fe10842e78b8be61f9e762b85ac952807d
     ports:
diff --git a/docker/up@cpu-offline/docker-compose.yml b/docker/up@cpu-offline/docker-compose.yml
@@ -2,14 +2,15 @@
 
 services:
   marker_app:
-    image: xiaoyao9184/marker:1.1.0
+    image: xiaoyao9184/marker:1.2.0
     container_name: marker_pdf_app
     environment:
       - TORCH_DEVICE=cpu
       - HF_HUB_OFFLINE=true
       - DETECTOR_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--vikp--surya_det3/snapshots/467ee9ec33e6e6c5f73e57dbc1415b14032f5b95
-      - LAYOUT_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--datalab-to--surya_layout0/snapshots/421ac206a400227ea714d47a405e53ce74374957
       - RECOGNITION_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--vikp--surya_rec2/snapshots/6611509b2c3a32c141703ce19adc899d9d0abf41
+      - LAYOUT_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--datalab-to--surya_layout/snapshots/7ac8e390226ee5fa2125dd303d827f79d31d1a1f
+      - OCR_ERROR_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--datalab-to--ocr_error_detection/snapshots/c1cbda3757670fd520553eaa5197656d331de414
       - TABLE_REC_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--vikp--surya_tablerec/snapshots/8bca165f81e9cee5fb382413eb23175079917d14
       - TEXIFY_MODEL_NAME=/root/.cache/huggingface/hub/models--vikp--texify/snapshots/ce49c1fe10842e78b8be61f9e762b85ac952807d
       # - FONT_DIR=/fonts # not work
diff --git a/docker/up@gpu-offline/docker-compose.yml b/docker/up@gpu-offline/docker-compose.yml
@@ -2,14 +2,15 @@
 
 services:
   marker_app:
-    image: xiaoyao9184/marker:1.1.0
+    image: xiaoyao9184/marker:1.2.0
     container_name: marker_pdf_app
     environment:
       - TORCH_DEVICE=cuda
       - HF_HUB_OFFLINE=true
       - DETECTOR_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--vikp--surya_det3/snapshots/467ee9ec33e6e6c5f73e57dbc1415b14032f5b95
-      - LAYOUT_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--datalab-to--surya_layout0/snapshots/421ac206a400227ea714d47a405e53ce74374957
       - RECOGNITION_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--vikp--surya_rec2/snapshots/6611509b2c3a32c141703ce19adc899d9d0abf41
+      - LAYOUT_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--datalab-to--surya_layout/snapshots/7ac8e390226ee5fa2125dd303d827f79d31d1a1f
+      - OCR_ERROR_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--datalab-to--ocr_error_detection/snapshots/c1cbda3757670fd520553eaa5197656d331de414
       - TABLE_REC_MODEL_CHECKPOINT=/root/.cache/huggingface/hub/models--vikp--surya_tablerec/snapshots/8bca165f81e9cee5fb382413eb23175079917d14
       - TEXIFY_MODEL_NAME=/root/.cache/huggingface/hub/models--vikp--texify/snapshots/ce49c1fe10842e78b8be61f9e762b85ac952807d
       # - FONT_DIR=/fonts # not work
diff --git a/environment.yml b/environment.yml
diff --git a/gradio/gradio_app.py b/gradio/gradio_app.py
diff --git a/gradio/requirements.txt b/gradio/requirements.txt
diff --git a/marker b/marker

Original file line number	Diff line number	Diff line change
`@@ -25,9 +25,9 @@`
`25`	`25`	`"command": "docker build -t xiaoyao9184/marker:master -f ./docker/build@source/dockerfile ."`
`26`	`26`	`},`
`27`	`27`	`{`
`28`		`- "label": "docker: build 1.1.0",`
	`28`	`+ "label": "docker: build 1.2.0",`
`29`	`29`	`"type": "shell",`
`30`		`- "command": "docker build -t xiaoyao9184/marker:1.1.0 -f ./docker/build@pypi/dockerfile ."`
	`30`	`+ "command": "docker build -t xiaoyao9184/marker:1.2.0 -f ./docker/build@pypi/dockerfile ."`
`31`	`31`	`},`
`32`	`32`	`{`
`33`	`33`	`"label": "huggingface-cli: download models",`
`@@ -45,7 +45,8 @@`
`45`	`45`	`"&& huggingface-cli download vikp/surya_rec2 --revision main --cache-dir ./cache/huggingface/hub",`
`46`	`46`	`"&& huggingface-cli download vikp/surya_tablerec --revision main --cache-dir ./cache/huggingface/hub",`
`47`	`47`	`"&& huggingface-cli download vikp/texify --revision main --cache-dir ./cache/huggingface/hub",`
`48`		`- "&& huggingface-cli download datalab-to/surya_layout0 --revision main --cache-dir ./cache/huggingface/hub",`
	`48`	`+ "&& huggingface-cli download datalab-to/surya_layout --revision main --cache-dir ./cache/huggingface/hub",`
	`49`	`+ "&& huggingface-cli download datalab-to/ocr_error_detection --revision main --cache-dir ./cache/huggingface/hub",`
`49`	`50`	`]`
`50`	`51`	`},`
`51`	`52`	`{`