Downloads · 30 days
20
30% of all-time downloads
thesimonharms/svtr-javanese-synthetic-v7
svtr-javanese-synthetic-v7 is a image-to-text model from thesimonharms. Use it when you need a caption or text from an image. It is set up for pytorch. The card lists the license as mit.
CTC line recognizer for printed Javanese Aksara on wide strips (height 48, width up to 1600). Fine-tuned from OpenOCR RepSVTR (mobile SVTRv2) with a new Javanese CTC head.
Downloads · 30 days
20
30% of all-time downloads
All-time downloads
67
Public
Repo size
17.9 MB
Likes
0
Public
Click a slice to open those files.
.pt17.9 MB · 100%
From the Hugging Face model README
CTC line recognizer for printed Javanese Aksara on wide strips (height 48, width up to 1600). Fine-tuned from OpenOCR RepSVTR (mobile SVTRv2) with a new Javanese CTC head.
This is not TrOCR. The short-line square specialist remains thesimonharms/trocr-javanese-synthetic-v6 (384×384, ≤12 aksara). Use v6 for short crops; use this checkpoint for longer printed lines.
| Part | Detail |
|---|---|
| Encoder | OpenOCR RepSVTR (RepViT / mobile SVTRv2), unfrozen |
| Head | New CTC head, Javanese block U+A980–U+A9DF + blank (~97 classes) |
| Input | One RGB line crop, resize height 48, keep aspect, cap width 1600. No pad-to-square. |
| Output | Greedy CTC decode (collapse repeats, drop blank) |
| Labels | 2–80 aksara |
SVTRv2 exists because encoder–decoder STR models collapse on long text; CTC does not (Du et al., ICCV 2025).
Held-out javanese-synthetic-long validation, greedy CTC decode.
| Bucket | n | Exact | CER | Near (edit ≤2) |
|---|---|---|---|---|
| Short (≤12) | 225 | 93.33% | 1.04% | 99.56% |
| Mid (13–24) | 300 | 91.67% | 0.67% | 98.67% |
| Long (25–40) | 450 | 93.56% | 0.30% | 99.11% |
| XLong (41+) | 525 | 79.62% | 0.51% | 97.71% |
| All | 1500 | 88.27% | 0.56% | 98.60% |
Use for
Do not use for
Resize a cropped line to height 48, keep aspect ratio, cap width at 1600. Do not pad to a square.
import sys
from huggingface_hub import snapshot_download
from PIL import Image
root = snapshot_download("thesimonharms/svtr-javanese-synthetic-v7")
sys.path.insert(0, root)
from infer import load_recognizer, recognize
model, codec, device = load_recognizer(root)
print(recognize(model, codec, Image.open("line.png"), device))
Private thesimonharms/javanese-synthetic-long: 80k train / 2.5k val, 2–80 aksara, 15% short / 20% mid / 30% long / 35% xlong, HarfBuzz-shaped Unicode Regular families, cream or white paper, light JPEG/blur only. No manuscript backgrounds. Hash holdout on text is the same scheme as v6.
OpenOCR / SVTRv2: Du et al., SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition, ICCV 2025.