---
license: apache-2.0
tags:
  - ocr
  - paddleocr
  - torq
  - synaptics
  - npu
library_name: torq
---

# PP-OCRv6-tiny for Torq (SL2619 NPU)

PP-OCRv6-tiny optical character recognition compiled for the Synaptics Torq NPU:
DBNet text detection followed by CTC text recognition. Both stages run on the
NPU. Used by the `ppocr` demo in
[torq-examples](https://github.com/synaptics-torq/torq-examples).

The recognition dictionary is Chinese + English (6,904 characters), so Latin
text, digits and punctuation decode natively; Japanese, Korean, Cyrillic and
Arabic are not covered.

| Input — `samples/sample.jpg` | NPU output — boxes + recognized text |
|:---:|:---:|
| <img src="https://huggingface.co/Synaptics/paddle-paddle-tiny/resolve/main/samples/sample.jpg" width="380"> | <img src="https://huggingface.co/Synaptics/paddle-paddle-tiny/resolve/main/assets/sample_ocr.jpg" width="380"> |

All ten lines are read correctly at confidence ≥ 0.966, in 1.7 s end to end on
an SL2619.

## Files

| File | Purpose |
|---|---|
| `ppocr_det_800x608.vmfb` | Detection (DBNet), static 800×608 bf16 input |
| `rec_buckets/rec_w320.vmfb` | Recognition, 48×320 lines |
| `rec_buckets/rec_w640.vmfb` | Recognition, 48×640 lines |
| `rec_buckets/rec_w1280.vmfb` | Recognition, 48×1280 lines |
| `rec_buckets/rec_w2432.vmfb` | Recognition, 48×2432 lines |
| `ppocr_rec.yml` | Recognizer character dictionary |
| `ppocr_det_dynamic.onnx` | fp32 detection, CPU reference for accuracy checks |
| `ppocr_rec_dynamic.onnx` | fp32 recognition, CPU reference for accuracy checks |
| `samples/sample.jpg` | Sample café menu card, 10 text lines |

### Why four recognition models

Recognition input width is static per vmfb. Each detected line is routed to the
narrowest bucket it fits in, so a short label is padded to 320 rather than to
the widest width. Lines longer than 2432 clamp to the widest bucket.

## Usage

```sh
git clone https://github.com/synaptics-torq/torq-examples
cd torq-examples
python setup_demos.py ppocr

cd ppocr
python src/infer.py \
  --image  ../models/Synaptics/paddle-paddle-tiny/samples/sample.jpg \
  --models ../models/Synaptics/paddle-paddle-tiny \
  --save-image
```

Either stage can be switched to ONNX Runtime with `--det-backend ort` /
`--rec-backend ort` (plus the matching `--det-onnx` / `--rec-onnx`) to compare
NPU output against a CPU reference.

## Measured on SL2619

`samples/sample.jpg`, 912×1200, 10 text lines detected:

| Stage | Time |
|---|---|
| Detection (800×608) | ~0.53 s |
| Recognition (10 lines, bucketed) | ~1.19 s |

Recognition scales with the number of detected lines, because each line is a
separate invocation — the bucket models are compiled with a static batch of 1.
A dense page of 99 lines takes roughly 22 s.

### About `sample.jpg`

A 912×1200 café menu card, rendered synthetically in DejaVu Serif rather than
photographed, so it carries no third-party image licensing.

Its width/height ratio of 0.76 matches the detector's static 608×800 input.
Preprocessing resizes straight to that shape without preserving aspect, so an
off-ratio image reaches the model stretched — worth matching if you swap in your
own sample.

Recognized output, all ten lines at confidence ≥ 0.966:

```
  1   [0.991] BLUE DOOR CAFE          6   [0.995] Smoked Salmon Bagel  9.75
  2   [0.996] all day breakfast       7   [1.000] DRINKS
  3   [0.999] BREAKFAST               8   [0.975] Espresso  2.75
  4   [0.996] Avocado Toast  6.50     9   [0.966] Fresh Orange Juice  4.00
  5   [0.996] Buttermilk Pancakes  7.00  10  [0.993] open 7am - 3pm daily
```