Main model is now D (2026-11-01), add 171 KB tiny variant

993b508 verified 1 day ago

6.31 kB

---
license: cc-by-nc-sa-4.0
language:
- tr
library_name: keras
pipeline_tag: image-to-text
tags:
- ocr
- text-recognition
- turkish
- tinyml
- tflite
- int8
- ctc
- microcontroller
---
# InviolusOCR: tiny Turkish line OCR for microcontrollers

A compact convolutional CTC recognizer for **one cropped line of printed
Turkish text**: 560,954 parameters and a **598 KB full-int8 TensorFlow Lite**
file that keeps almost all of the float model's accuracy. A half-width **tiny**
variant is **171 KB**.

*Keywords: Turkish OCR, Türkçe OCR, tiny OCR, text recognition, TFLite, int8,
TinyML, ESP32, microcontroller.*

> **Türkçe özet:** Mikrodenetleyiciler için tek satır Türkçe metin okuyan,
> 561 bin parametreli, int8 TFLite dosyası 598 KB olan küçük bir OCR modeli.
> int8 hâli, ayrılmış test satırlarının %77,3'ünü, gerçek sahne metni
> (TS-TR) kırpıntılarının %56,2'sini ve basılı belge satırlarının (donut)
> %46,5'ini harfi harfine doğru okuyor. 171 KB'lık küçük sürüm daha düşük
> doğrulukta çalışıyor (%64,4 / %32,6 / %20,1). Ticari olmayan kullanım içindir
> (CC BY-NC-SA 4.0).

This replaces [inviolus/erdem-ocr-tr-tinyml](https://huggingface.co/inviolus/erdem-ocr-tr-tinyml)
(2026-10-09), whose int8 file lost most of its accuracy.

## Files

| File | What it is |
|---|---|
| `inviolusocr.keras` | Float model, input `(batch, 32, 160, 1)`, output `(batch, 40, 90)` softmax |
| `inviolusocr_int8.tflite` | Full-int8 export, input `[1, 32, 160, 1]` int8 (scale 0.007843, zero point -1), output `[1, 40, 90]` int8 (scale 0.00390625, zero point -128) |
| `inviolusocr_tiny.keras`, `inviolusocr_tiny_int8.tflite` | Half-width variant, 144,330 parameters, same input, output and alphabet |
| `alphabet.json` | Character set used to decode the output |
| `benchmark.json`, `benchmark_T.json` | Scores for this model and the earlier versions; scores for tiny |

## Model

- **Input:** one horizontal text line, grayscale, resized to 160×32, scaled
  to `[-1, 1]` (`pixel / 127.5 - 1`).
- **Architecture:** 4 conv + batch-norm + pool blocks, a dense projection,
  then four residual dilated 1-D convolutions (dilation 1, 2, 4, 1) instead of
  an LSTM, and a dense softmax. Only ops that quantize cleanly to int8.
- **Output:** 40 timesteps × 90 classes. Class `0` is padding, `1..88` are the
  characters of `alphabet.json` in order, `89` is the CTC blank.
- **Character set:** digits, ASCII letters, `ç ğ ı İ ö ş ü Ç Ğ Ö Ş Ü`, space
  and `.,:;!?-_/()'%`. Up to 24 characters per line.
- **Not included:** text detection. The line must already be cropped.

## Usage

```python
import json
import numpy as np
import tensorflow as tf
alphabet = json.load(open("alphabet.json", encoding="utf-8"))["alphabet"]
BLANK = len(alphabet) + 1
def preprocess(path):
    image = tf.io.decode_image(tf.io.read_file(path), channels=1, expand_animations=False)
    image = tf.image.resize(image, [32, 160])
    return (tf.cast(image, tf.float32) / 127.5 - 1.0).numpy()
def decode(ids):
    text, previous = [], None
    for i in ids:
        if i != previous and 0 < i < BLANK:
            text.append(alphabet[i - 1])
        previous = i
    return "".join(text)
# int8 TFLite (the file meant for devices)
interpreter = tf.lite.Interpreter(model_path="inviolusocr_int8.tflite")
interpreter.allocate_tensors()
inp, out = interpreter.get_input_details()[0], interpreter.get_output_details()[0]
scale, zero = inp["quantization"]
x = np.clip(np.round(preprocess("line.png") / scale + zero), -128, 127).astype(np.int8)
interpreter.set_tensor(inp["index"], x[np.newaxis])
interpreter.invoke()
print(decode(interpreter.get_tensor(out["index"])[0].argmax(-1)))
```

## Results

Exact-line accuracy (the whole line correct), all models scored on the same
rows: 12,093 held-out lines (synthetic, Zenodo, TS-TR, esengul3, STS-TR) and
the 2,078-crop official TS-TR test split (real scene text, never trained on),
plus 2,563 printed-document rows from the donut 200k test list.

![Exact-line accuracy of the int8 files of the main and tiny models](benchmark-1102-size-light.svg)

| Model, int8 file | Params | Size | Held-out | TS-TR | Donut test |
|---|---:|---:|---:|---:|---:|
| erdem-ocr 2026-10-09 (LSTM) | 631,226 | 665 KB | 32.9% | 33.5% | not measured |
| InviolusOCR 2026-10-31 (previous version here) | 560,954 | 598 KB | 78.4% | 58.2% | 9.3% |
| **InviolusOCR 2026-11-01 (main)** | **560,954** | **598 KB** | **77.3%** | **56.2%** | **46.5%** |
| **InviolusOCR tiny 2026-11-02** | **144,330** | **171 KB** | 64.4% | 32.6% | 20.1% |

Character error rate of the int8 files: main 10.0% held-out, 18.8% TS-TR, 12.6%
donut; tiny 14.1%, 31.3%, 24.1%.

## Limitations

- Printed text only; no handwriting, curved text or full pages.
- Real scene text is still the weak spot (56% exact).
- **Licence plates are not read** (2% exact on 250 plate crops in a first,
  unchecked test).
- Not yet measured on a microcontroller (speed, memory).
- Text detection and line cropping must be done before this model runs.

## Training data

About 106,000 training crops. The main model was continued from earlier
weights; tiny was trained from scratch for 260 minutes on CPU.

- Synthetic Turkish lines rendered from a 50k-word Turkish word list.
- [Turkish OCR Text Image Dataset](https://zenodo.org/records/21923181), Zenodo, CC BY 4.0.
- [Turkish Scene Text Recognition (TS-TR)](https://www.kaggle.com/datasets/serdaryildiz/turkish-scene-text-recognition-dataset), Serdar Yıldız, CC BY-NC 4.0.
- [Synthetic Turkish Scene Text (STS-TR)](https://www.kaggle.com/datasets/serdaryildiz/synthetic-turkish-scene-text-recognition-dataset), Serdar Yıldız, CC BY-NC 4.0.
- [Turkish Word OCR](https://huggingface.co/datasets/esengul3/turkish-word-ocr), esengul3, CC BY-SA 4.0.
- Turkish recognition 200k v4 (donut), turgutguvercin, CC BY-SA 4.0.

## License

Because of the non-commercial (TS-TR, STS-TR) and share-alike (esengul3, donut)
terms of the training data, this model is released under
**[CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)**:
non-commercial use only, credit this model and the datasets above, and share
adaptations under the same license.

Training code (MIT): [ErdemWilkinson/InviolusOCR](https://github.com/ErdemWilkinson/InviolusOCR).

	---
	license: cc-by-nc-sa-4.0
	language:
	- tr
	library_name: keras
	pipeline_tag: image-to-text
	tags:
	- ocr
	- text-recognition
	- turkish
	- tinyml
	- tflite
	- int8
	- ctc
	- microcontroller
	---

	# InviolusOCR: tiny Turkish line OCR for microcontrollers

	A compact convolutional CTC recognizer for **one cropped line of printed
	Turkish text: 560,954 parameters and a 598 KB full-int8 TensorFlow Lite**
	file that keeps almost all of the float model's accuracy. A half-width tiny
	variant is 171 KB.

	*Keywords: Turkish OCR, Türkçe OCR, tiny OCR, text recognition, TFLite, int8,
	TinyML, ESP32, microcontroller.*

	> Türkçe özet: Mikrodenetleyiciler için tek satır Türkçe metin okuyan,
	> 561 bin parametreli, int8 TFLite dosyası 598 KB olan küçük bir OCR modeli.
	> int8 hâli, ayrılmış test satırlarının %77,3'ünü, gerçek sahne metni
	> (TS-TR) kırpıntılarının %56,2'sini ve basılı belge satırlarının (donut)
	> %46,5'ini harfi harfine doğru okuyor. 171 KB'lık küçük sürüm daha düşük
	> doğrulukta çalışıyor (%64,4 / %32,6 / %20,1). Ticari olmayan kullanım içindir
	> (CC BY-NC-SA 4.0).

	This replaces [inviolus/erdem-ocr-tr-tinyml](https://huggingface.co/inviolus/erdem-ocr-tr-tinyml)
	(2026-10-09), whose int8 file lost most of its accuracy.

	## Files

	\| File \| What it is \|
	\|---\|---\|
	\| `inviolusocr.keras` \| Float model, input `(batch, 32, 160, 1)`, output `(batch, 40, 90)` softmax \|
	\| `inviolusocr_int8.tflite` \| Full-int8 export, input `[1, 32, 160, 1]` int8 (scale 0.007843, zero point -1), output `[1, 40, 90]` int8 (scale 0.00390625, zero point -128) \|
	\| `inviolusocr_tiny.keras`, `inviolusocr_tiny_int8.tflite` \| Half-width variant, 144,330 parameters, same input, output and alphabet \|
	\| `alphabet.json` \| Character set used to decode the output \|
	\| `benchmark.json`, `benchmark_T.json` \| Scores for this model and the earlier versions; scores for tiny \|

	## Model

	- Input: one horizontal text line, grayscale, resized to 160×32, scaled
	to `[-1, 1]` (`pixel / 127.5 - 1`).
	- Architecture: 4 conv + batch-norm + pool blocks, a dense projection,
	then four residual dilated 1-D convolutions (dilation 1, 2, 4, 1) instead of
	an LSTM, and a dense softmax. Only ops that quantize cleanly to int8.
	- Output: 40 timesteps × 90 classes. Class `0` is padding, `1..88` are the
	characters of `alphabet.json` in order, `89` is the CTC blank.
	- Character set: digits, ASCII letters, `ç ğ ı İ ö ş ü Ç Ğ Ö Ş Ü`, space
	and `.,:;!?-_/()'%`. Up to 24 characters per line.
	- Not included: text detection. The line must already be cropped.

	## Usage

	```python
	import json
	import numpy as np
	import tensorflow as tf

	alphabet = json.load(open("alphabet.json", encoding="utf-8"))["alphabet"]
	BLANK = len(alphabet) + 1

	def preprocess(path):
	image = tf.io.decode_image(tf.io.read_file(path), channels=1, expand_animations=False)
	image = tf.image.resize(image, [32, 160])
	return (tf.cast(image, tf.float32) / 127.5 - 1.0).numpy()

	def decode(ids):
	text, previous = [], None
	for i in ids:
	if i != previous and 0 < i < BLANK:
	text.append(alphabet[i - 1])
	previous = i
	return "".join(text)

	# int8 TFLite (the file meant for devices)
	interpreter = tf.lite.Interpreter(model_path="inviolusocr_int8.tflite")
	interpreter.allocate_tensors()
	inp, out = interpreter.get_input_details()[0], interpreter.get_output_details()[0]
	scale, zero = inp["quantization"]
	x = np.clip(np.round(preprocess("line.png") / scale + zero), -128, 127).astype(np.int8)
	interpreter.set_tensor(inp["index"], x[np.newaxis])
	interpreter.invoke()
	print(decode(interpreter.get_tensor(out["index"])[0].argmax(-1)))
	```

	## Results

	Exact-line accuracy (the whole line correct), all models scored on the same
	rows: 12,093 held-out lines (synthetic, Zenodo, TS-TR, esengul3, STS-TR) and
	the 2,078-crop official TS-TR test split (real scene text, never trained on),
	plus 2,563 printed-document rows from the donut 200k test list.

	![Exact-line accuracy of the int8 files of the main and tiny models](benchmark-1102-size-light.svg)

	\| Model, int8 file \| Params \| Size \| Held-out \| TS-TR \| Donut test \|
	\|---\|---:\|---:\|---:\|---:\|---:\|
	\| erdem-ocr 2026-10-09 (LSTM) \| 631,226 \| 665 KB \| 32.9% \| 33.5% \| not measured \|
	\| InviolusOCR 2026-10-31 (previous version here) \| 560,954 \| 598 KB \| 78.4% \| 58.2% \| 9.3% \|
	\| InviolusOCR 2026-11-01 (main) \| 560,954 \| 598 KB \| 77.3% \| 56.2% \| 46.5% \|
	\| InviolusOCR tiny 2026-11-02 \| 144,330 \| 171 KB \| 64.4% \| 32.6% \| 20.1% \|

	Character error rate of the int8 files: main 10.0% held-out, 18.8% TS-TR, 12.6%
	donut; tiny 14.1%, 31.3%, 24.1%.

	## Limitations

	- Printed text only; no handwriting, curved text or full pages.
	- Real scene text is still the weak spot (56% exact).
	- Licence plates are not read (2% exact on 250 plate crops in a first,
	unchecked test).
	- Not yet measured on a microcontroller (speed, memory).
	- Text detection and line cropping must be done before this model runs.

	## Training data

	About 106,000 training crops. The main model was continued from earlier
	weights; tiny was trained from scratch for 260 minutes on CPU.

	- Synthetic Turkish lines rendered from a 50k-word Turkish word list.
	- [Turkish OCR Text Image Dataset](https://zenodo.org/records/21923181), Zenodo, CC BY 4.0.
	- [Turkish Scene Text Recognition (TS-TR)](https://www.kaggle.com/datasets/serdaryildiz/turkish-scene-text-recognition-dataset), Serdar Yıldız, CC BY-NC 4.0.
	- [Synthetic Turkish Scene Text (STS-TR)](https://www.kaggle.com/datasets/serdaryildiz/synthetic-turkish-scene-text-recognition-dataset), Serdar Yıldız, CC BY-NC 4.0.
	- [Turkish Word OCR](https://huggingface.co/datasets/esengul3/turkish-word-ocr), esengul3, CC BY-SA 4.0.
	- Turkish recognition 200k v4 (donut), turgutguvercin, CC BY-SA 4.0.

	## License

	Because of the non-commercial (TS-TR, STS-TR) and share-alike (esengul3, donut)
	terms of the training data, this model is released under
	[CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/):
	non-commercial use only, credit this model and the datasets above, and share
	adaptations under the same license.

	Training code (MIT): [ErdemWilkinson/InviolusOCR](https://github.com/ErdemWilkinson/InviolusOCR).