Instructions to use duyle2408/trocr-vietnamese-handwriting with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use duyle2408/trocr-vietnamese-handwriting with Transformers:

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

pipe = pipeline("image-text-to-text", model="duyle2408/trocr-vietnamese-handwriting")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("duyle2408/trocr-vietnamese-handwriting")
model = AutoModelForImageTextToText.from_pretrained("duyle2408/trocr-vietnamese-handwriting")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use duyle2408/trocr-vietnamese-handwriting with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "duyle2408/trocr-vietnamese-handwriting"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "duyle2408/trocr-vietnamese-handwriting",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/duyle2408/trocr-vietnamese-handwriting

SGLang

How to use duyle2408/trocr-vietnamese-handwriting 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 "duyle2408/trocr-vietnamese-handwriting" \
    --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": "duyle2408/trocr-vietnamese-handwriting",
		"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 "duyle2408/trocr-vietnamese-handwriting" \
        --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": "duyle2408/trocr-vietnamese-handwriting",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use duyle2408/trocr-vietnamese-handwriting with Docker Model Runner:
```
docker model run hf.co/duyle2408/trocr-vietnamese-handwriting
```

TrOCR Vietnamese Handwriting

This model is a fine-tuned version of microsoft/trocr-large-handwritten
on a Vietnamese handwriting dataset.

Results

eval_loss: 5.02
eval_runtime: 113.95
eval_samples_per_second: 10.76
eval_steps_per_second: 2.69

Model description

VisionEncoderDecoder (ViT + TrOCR) model trained for Vietnamese OCR.

Downloads last month: 92

Safetensors

Model size

0.5B params

Tensor type

F32

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support