magic-pdf 1.2.2__py3-none-any.whl → 1.3.0__py3-none-any.whl

magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/arch_config.yaml

@@ -0,0 +1,383 @@
+ch_ptocr_mobile_v2.0_cls_infer:
+  model_type: cls
+  algorithm: CLS
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.35
+    model_name: small
+  Neck:
+  Head:
+    name: ClsHead
+    class_dim: 2
+
+Multilingual_PP-OCRv3_det_infer:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+    disable_se: True
+  Neck:
+    name: RSEFPN
+    out_channels: 96
+    shortcut: True
+  Head:
+    name: DBHead
+    k: 50
+
+en_PP-OCRv3_det_infer:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+    disable_se: True
+  Neck:
+    name: RSEFPN
+    out_channels: 96
+    shortcut: True
+  Head:
+    name: DBHead
+    k: 50
+
+ch_PP-OCRv3_det_infer:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+    disable_se: True
+  Neck:
+    name: RSEFPN
+    out_channels: 96
+    shortcut: True
+  Head:
+    name: DBHead
+    k: 50
+
+en_PP-OCRv4_rec_infer:
+  model_type: rec
+  algorithm: SVTR_LCNet
+  Transform:
+  Backbone:
+    name: PPLCNetV3
+    scale: 0.95
+  Head:
+    name: MultiHead
+    out_channels_list:
+      CTCLabelDecode: 97 #'blank' + ...(62) + ' '
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 120
+            depth: 2
+            hidden_dims: 120
+            kernel_size: [ 1, 3 ]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: 25
+
+ch_PP-OCRv4_det_infer:
+  model_type: det
+  algorithm: DB
+  Transform: null
+  Backbone:
+    name: PPLCNetV3
+    scale: 0.75
+    det: True
+  Neck:
+    name: RSEFPN
+    out_channels: 96
+    shortcut: True
+  Head:
+    name: DBHead
+    k: 50
+
+ch_PP-OCRv4_det_server_infer:
+  model_type: det
+  algorithm: DB
+  Transform: null
+  Backbone:
+    name: PPHGNet_small
+    det: True
+  Neck:
+    name: LKPAN
+    out_channels: 256
+    intracl: true
+  Head:
+    name: PFHeadLocal
+    k: 50
+    mode: "large"
+
+ch_PP-OCRv4_rec_infer:
+  model_type: rec
+  algorithm: SVTR_LCNet
+  Transform:
+  Backbone:
+    name: PPLCNetV3
+    scale: 0.95
+  Head:
+    name: MultiHead
+    out_channels_list:
+      CTCLabelDecode: 6625 #'blank' + ...(6623) + ' '
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 120
+            depth: 2
+            hidden_dims: 120
+            kernel_size: [ 1, 3 ]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: 25
+
+ch_PP-OCRv4_rec_server_infer:
+  model_type: rec
+  algorithm: SVTR_HGNet
+  Transform:
+  Backbone:
+    name: PPHGNet_small
+  Head:
+    name: MultiHead
+    out_channels_list:
+      CTCLabelDecode: 6625 #'blank' + ...(6623) + ' '
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 120
+            depth: 2
+            hidden_dims: 120
+            kernel_size: [ 1, 3 ]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: 25
+
+chinese_cht_PP-OCRv3_rec_infer:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Neck:
+    name: SequenceEncoder
+    encoder_type: svtr
+    dims: 64
+    depth: 2
+    hidden_dims: 120
+    use_guide: True
+  Head:
+    name: CTCHead
+#    out_channels: 8423
+    fc_decay: 0.00001
+
+latin_PP-OCRv3_rec_infer:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [ 1, 2 ]
+    last_pool_type: avg
+  Neck:
+    name: SequenceEncoder
+    encoder_type: svtr
+    dims: 64
+    depth: 2
+    hidden_dims: 120
+    use_guide: True
+  Head:
+    name: CTCHead
+#    out_channels: 187
+    fc_decay: 0.00001
+
+cyrillic_PP-OCRv3_rec_infer:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [ 1, 2 ]
+    last_pool_type: avg
+  Neck:
+    name: SequenceEncoder
+    encoder_type: svtr
+    dims: 64
+    depth: 2
+    hidden_dims: 120
+    use_guide: True
+  Head:
+    name: CTCHead
+#    out_channels: 165
+    fc_decay: 0.00001
+
+arabic_PP-OCRv3_rec_infer:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [ 1, 2 ]
+    last_pool_type: avg
+  Neck:
+    name: SequenceEncoder
+    encoder_type: svtr
+    dims: 64
+    depth: 2
+    hidden_dims: 120
+    use_guide: True
+  Head:
+    name: CTCHead
+#    out_channels: 164
+    fc_decay: 0.00001
+
+korean_PP-OCRv3_rec_infer:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [ 1, 2 ]
+    last_pool_type: avg
+  Neck:
+    name: SequenceEncoder
+    encoder_type: svtr
+    dims: 64
+    depth: 2
+    hidden_dims: 120
+    use_guide: True
+  Head:
+    name: CTCHead
+#    out_channels: 3690
+    fc_decay: 0.00001
+
+japan_PP-OCRv3_rec_infer:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [ 1, 2 ]
+    last_pool_type: avg
+  Neck:
+    name: SequenceEncoder
+    encoder_type: svtr
+    dims: 64
+    depth: 2
+    hidden_dims: 120
+    use_guide: True
+  Head:
+    name: CTCHead
+#    out_channels: 4401
+    fc_decay: 0.00001
+
+ta_PP-OCRv3_rec_infer:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [ 1, 2 ]
+    last_pool_type: avg
+  Neck:
+    name: SequenceEncoder
+    encoder_type: svtr
+    dims: 64
+    depth: 2
+    hidden_dims: 120
+    use_guide: True
+  Head:
+    name: CTCHead
+#    out_channels: 130
+    fc_decay: 0.00001
+
+te_PP-OCRv3_rec_infer:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [ 1, 2 ]
+    last_pool_type: avg
+  Neck:
+    name: SequenceEncoder
+    encoder_type: svtr
+    dims: 64
+    depth: 2
+    hidden_dims: 120
+    use_guide: True
+  Head:
+    name: CTCHead
+#    out_channels: 153
+    fc_decay: 0.00001
+
+ka_PP-OCRv3_rec_infer:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [ 1, 2 ]
+    last_pool_type: avg
+  Neck:
+    name: SequenceEncoder
+    encoder_type: svtr
+    dims: 64
+    depth: 2
+    hidden_dims: 120
+    use_guide: True
+  Head:
+    name: CTCHead
+#    out_channels: 155
+    fc_decay: 0.00001
+
+devanagari_PP-OCRv3_rec_infer:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [ 1, 2 ]
+    last_pool_type: avg
+  Neck:
+    name: SequenceEncoder
+    encoder_type: svtr
+    dims: 64
+    depth: 2
+    hidden_dims: 120
+    use_guide: True
+  Head:
+    name: CTCHead
+#    out_channels: 169
+    fc_decay: 0.00001
+

magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/arabic_dict.txt

@@ -0,0 +1,162 @@
+ 
+!
+#
+$
+%
+&
+'
+(
++
+,
+-
+.
+/
+0
+1
+2
+3
+4
+5
+6
+7
+8
+9
+:
+?
+@
+A
+B
+C
+D
+E
+F
+G
+H
+I
+J
+K
+L
+M
+N
+O
+P
+Q
+R
+S
+T
+U
+V
+W
+X
+Y
+Z
+_
+a
+b
+c
+d
+e
+f
+g
+h
+i
+j
+k
+l
+m
+n
+o
+p
+q
+r
+s
+t
+u
+v
+w
+x
+y
+z
+É
+é
+ء
+آ
+أ
+ؤ
+إ
+ئ
+ا
+ب
+ة
+ت
+ث
+ج
+ح
+خ
+د
+ذ
+ر
+ز
+س
+ش
+ص
+ض
+ط
+ظ
+ع
+غ
+ف
+ق
+ك
+ل
+م
+ن
+ه
+و
+ى
+ي
+ً
+ٌ
+ٍ
+َ
+ُ
+ِ
+ّ
+ْ
+ٓ
+ٔ
+ٰ
+ٱ
+ٹ
+پ
+چ
+ڈ
+ڑ
+ژ
+ک
+ڭ
+گ
+ں
+ھ
+ۀ
+ہ
+ۂ
+ۃ
+ۆ
+ۇ
+ۈ
+ۋ
+ی
+ې
+ے
+ۓ
+ە
+١
+٢
+٣
+٤
+٥
+٦
+٧
+٨
+٩