Instructions to use PiotrSty/trocr-pl-mixed-aug-light-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PiotrSty/trocr-pl-mixed-aug-light-v1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="PiotrSty/trocr-pl-mixed-aug-light-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("PiotrSty/trocr-pl-mixed-aug-light-v1")
model = AutoModelForMultimodalLM.from_pretrained("PiotrSty/trocr-pl-mixed-aug-light-v1", device_map="auto")

PEFT
How to use PiotrSty/trocr-pl-mixed-aug-light-v1 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PiotrSty/trocr-pl-mixed-aug-light-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PiotrSty/trocr-pl-mixed-aug-light-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PiotrSty/trocr-pl-mixed-aug-light-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PiotrSty/trocr-pl-mixed-aug-light-v1

SGLang

How to use PiotrSty/trocr-pl-mixed-aug-light-v1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "PiotrSty/trocr-pl-mixed-aug-light-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PiotrSty/trocr-pl-mixed-aug-light-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "PiotrSty/trocr-pl-mixed-aug-light-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PiotrSty/trocr-pl-mixed-aug-light-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PiotrSty/trocr-pl-mixed-aug-light-v1 with Docker Model Runner:
```
docker model run hf.co/PiotrSty/trocr-pl-mixed-aug-light-v1
```

PiotrSty/trocr-pl-mixed-aug-light-v1 (experimental)

Fine-tune of PiotrSty/trocr-pl-base on synthetic Polish print + real EHRI typewritten Polish lines + 3× light-augmented EHRI train lines. run 6 used medium augmentations (5×) which improved typewriter but regressed print (5.36% → 7.37%). This run uses light strength (blur+noise only, no gamma/JPEG/contrast) with 3× copies to test if gentler augmentations avoid the print regression while keeping the typewriter gain.

Training

Base: PiotrSty/trocr-pl-base
Method: QLoRA on decoder attention (q/k/v/out_proj), rank 16, alpha 32
Train: 2000 synthetic + 349 real EHRI + 698 light-augmented EHRI = 3047 lines
Val: 38 EHRI lines (held-out doc ZIH3010905, not augmented)
Epochs: 15, batch 8, lr 1e-4, T4 x2
Best checkpoint: /kaggle/working/trocr-pl-run7/checkpoint-1410 (val CER 0.2777, WER 0.6456)
Document-level split, no line leakage. Light augmentations only on train.

Evaluation on frozen held-out sets

Model	EHRI test (81, typewriter)	real-lines-v1 (75, print)
trocr-pl-base (run2)	CER 47.30% / WER 90.82%	CER 11.11% / WER 35.84%
trocr-pl-mixed-v3 (run5, 30 ep)	CER 29.74% / WER 74.96%	CER 5.36% / WER 22.88%
trocr-pl-mixed-aug-v1 (run6, 15 ep + medium aug 5×)	CER 27.30% / WER 69.83%	CER 7.37% / WER 26.72%
trocr-pl-mixed-aug-light-v1 (run7, 15 ep + light aug 3×)	(fill from eval cell)	(fill from eval cell)

Limitations

Line recognizer only; page segmentation on faded typewriter is unreliable.
Augmentations are synthetic; real data diversity still matters.
Do NOT use as drop-in replacement without your own eval.

Provenance

See run.json, selection.json, best_metrics.json in this repo. Source: https://github.com/PiotrStyla/OCR_engine (commit 9911c81) EHRI dataset: https://huggingface.co/datasets/PiotrSty/ehri-pl-lines

Downloads last month: 15

Safetensors

Model size

0.3B params

Tensor type

F32

Model tree for PiotrSty/trocr-pl-mixed-aug-light-v1

Base model

microsoft/trocr-base-printed

Finetuned

PiotrSty/trocr-pl-base

Finetuned

(4)

this model