[sync] doctr vocabs

felixdittrich92 · Aug 23, 2024 · 08052bb · 08052bb
1 parent 4818b94
commit 08052bb
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 1 deletion.
diff --git a/onnxtr/models/builder.py b/onnxtr/models/builder.py
@@ -266,7 +266,7 @@ def _build_blocks(
                 Line([
                     Word(
                         *word_preds[idx],
-                        tuple([tuple(pt) for pt in boxes[idx].tolist()]),  # type: ignore[arg-type]
+                        tuple(tuple(pt) for pt in boxes[idx].tolist()),  # type: ignore[arg-type]
                         float(objectness_scores[idx]),
                         crop_orientations[idx],
                     )

diff --git a/onnxtr/utils/vocabs.py b/onnxtr/utils/vocabs.py
@@ -25,6 +25,7 @@
     "hindi_punctuation": "।,?!:्ॐ॰॥॰",
     "bangla_letters": "অআইঈউঊঋএঐওঔকখগঘঙচছজঝঞটঠডঢণতথদধনপফবভমযরলশষসহ়ঽািীুূৃেৈোৌ্ৎংঃঁ",
     "bangla_digits": "০১২৩৪৫৬৭৮৯",
+    "generic_cyrillic_letters": "абвгдежзийклмнопрстуфхцчшщьюяАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЬЮЯ",
 }
 
 VOCABS["latin"] = VOCABS["digits"] + VOCABS["ascii_letters"] + VOCABS["punctuation"]
@@ -59,6 +60,9 @@
 VOCABS["hebrew"] = VOCABS["english"] + "אבגדהוזחטיכלמנסעפצקרשת" + "₪"
 VOCABS["hindi"] = VOCABS["hindi_letters"] + VOCABS["hindi_digits"] + VOCABS["hindi_punctuation"]
 VOCABS["bangla"] = VOCABS["bangla_letters"] + VOCABS["bangla_digits"]
+VOCABS["ukrainian"] = (
+    VOCABS["generic_cyrillic_letters"] + VOCABS["digits"] + VOCABS["punctuation"] + VOCABS["currency"] + "ґіїєҐІЇЄ₴"
+)
 VOCABS["multilingual"] = "".join(
     dict.fromkeys(
         VOCABS["french"]