Instructions to use yzk/trocr-large-printed-vedic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yzk/trocr-large-printed-vedic with Transformers:

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

pipe = pipeline("image-text-to-text", model="yzk/trocr-large-printed-vedic")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("yzk/trocr-large-printed-vedic")
model = AutoModelForImageTextToText.from_pretrained("yzk/trocr-large-printed-vedic")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use yzk/trocr-large-printed-vedic with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yzk/trocr-large-printed-vedic

SGLang

How to use yzk/trocr-large-printed-vedic 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 "yzk/trocr-large-printed-vedic" \
    --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": "yzk/trocr-large-printed-vedic",
		"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 "yzk/trocr-large-printed-vedic" \
        --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": "yzk/trocr-large-printed-vedic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yzk/trocr-large-printed-vedic with Docker Model Runner:
```
docker model run hf.co/yzk/trocr-large-printed-vedic
```

Model Card for Model ID

OCR for Vedic texts printed in Devanagari.

Note This version is limited to a type of texts with accents marked by vertical lines over Devanagari characters.

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: https://huggingface.co/yzk
Funded by: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-23K18646/
Training Details

Training Data

Schroeder's edition of Maitrāyaṇī Sam̐hitā: https://huggingface.co/datasets/yzk/veda-ocr-ms (will be public)

Training Hyperparameters
- Training regime: [More Information Needed]
```
params:
  max_length: 512
  train_batch_size: 16
  eval_batch_size: 16 
  learning_rate: 2e-5
  weight_decay: 0.01
  save_total_limit: 3
  num_train_epochs: 20
  logging_steps: 2
  save_steps: 2000
  eval_steps: 200
```
Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Downloads last month: 8

Safetensors

Model size

0.6B params

Tensor type

F32

Inference Providers NEW

Image-Text-to-Text

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

Model tree for yzk/trocr-large-printed-vedic

Base model

microsoft/trocr-large-printed

Finetuned

(7)

this model

Dataset used to train yzk/trocr-large-printed-vedic

Paper for yzk/trocr-large-printed-vedic

Quantifying the Carbon Emissions of Machine Learning

Paper • 1910.09700 • Published Oct 21, 2019 • 46

Model Card for Model ID

Model Details

Model Description

Training Details

Training Data

Training Hyperparameters

Evaluation

Testing Data, Factors & Metrics

Testing Data

Factors

Metrics

Results

Summary

Citation [optional]

Model tree for yzk/trocr-large-printed-vedic

Dataset used to train yzk/trocr-large-printed-vedic

Paper for yzk/trocr-large-printed-vedic