Skip to content

Commit 484618e

Browse files
artizclaude
andcommitted
wasm demos: working cyrillic recognition model URL
SWHL/RapidOCR ships no cyrillic PP-OCRv3 export — the previous URL 404'd and ort-web choked on the HTML error page ("protobuf parsing failed"). Point the cyrillic entry at the cycloneboy/cyrillic_PP-OCRv3_rec_infer HF repo instead, which carries both the ONNX export and its paired 163-char dictionary (verified: output tensor is [n, t, 165] = blank + dict + space, matching dict_chars' table layout). Refs #157 Signed-off-by: artiz <artem.kustikov@gmail.com> Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01EY5KAiquN4YpVf2PXEQkVT
1 parent fa72393 commit 484618e

2 files changed

Lines changed: 4 additions & 4 deletions

File tree

crates/docling-wasm/www/ocr.html

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -61,8 +61,8 @@ <h1>docling.rs → wasm: OCR a scanned image in your browser</h1>
6161
dict: "https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/main/ppocr/utils/en_dict.txt",
6262
},
6363
cyrillic: {
64-
model: "https://huggingface.co/SWHL/RapidOCR/resolve/main/PP-OCRv3/cyrillic_PP-OCRv3_rec_infer.onnx",
65-
dict: "https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/main/ppocr/utils/dict/cyrillic_dict.txt",
64+
model: "https://huggingface.co/cycloneboy/cyrillic_PP-OCRv3_rec_infer/resolve/main/model.onnx",
65+
dict: "https://huggingface.co/cycloneboy/cyrillic_PP-OCRv3_rec_infer/resolve/main/cyrillic_dict.txt",
6666
},
6767
ch: {
6868
model: "https://huggingface.co/SWHL/RapidOCR/resolve/main/PP-OCRv3/ch_PP-OCRv3_rec_infer.onnx",

crates/docling-wasm/www/scan.html

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -69,8 +69,8 @@ <h1>docling.rs → wasm: scanned PDF / image, full lite profile</h1>
6969
dict: "https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/main/ppocr/utils/en_dict.txt",
7070
},
7171
cyrillic: {
72-
model: "https://huggingface.co/SWHL/RapidOCR/resolve/main/PP-OCRv3/cyrillic_PP-OCRv3_rec_infer.onnx",
73-
dict: "https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/main/ppocr/utils/dict/cyrillic_dict.txt",
72+
model: "https://huggingface.co/cycloneboy/cyrillic_PP-OCRv3_rec_infer/resolve/main/model.onnx",
73+
dict: "https://huggingface.co/cycloneboy/cyrillic_PP-OCRv3_rec_infer/resolve/main/cyrillic_dict.txt",
7474
},
7575
ch: {
7676
model: "https://huggingface.co/SWHL/RapidOCR/resolve/main/PP-OCRv3/ch_PP-OCRv3_rec_infer.onnx",

0 commit comments

Comments
 (0)