Image-Text-to-Text
Transformers
PyTorch
English
Chinese
multilingual
vision-encoder-decoder
Image-to-Text
OCR
Image-Captioning
Text-Recognition
Instructions to use priyank-m/m_OCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use priyank-m/m_OCR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="priyank-m/m_OCR")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("priyank-m/m_OCR") model = AutoModelForImageTextToText.from_pretrained("priyank-m/m_OCR") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use priyank-m/m_OCR with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "priyank-m/m_OCR" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "priyank-m/m_OCR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/priyank-m/m_OCR
- SGLang
How to use priyank-m/m_OCR 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 "priyank-m/m_OCR" \ --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": "priyank-m/m_OCR", "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 "priyank-m/m_OCR" \ --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": "priyank-m/m_OCR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use priyank-m/m_OCR with Docker Model Runner:
docker model run hf.co/priyank-m/m_OCR
Add multilingual to the language tag
#1
by lbourdois - opened
README.md
CHANGED
|
@@ -1,15 +1,16 @@
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
-
|
| 4 |
-
|
|
|
|
| 5 |
tags:
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
datasets:
|
| 10 |
-
|
| 11 |
metrics:
|
| 12 |
-
|
| 13 |
---
|
| 14 |
|
| 15 |
Multilingual OCR (m_OCR) is a VisionEncoderDecoder model based on the concept of TrOCR for English and Chinese document text-recognition.
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
+
- en
|
| 4 |
+
- zh
|
| 5 |
+
- multilingual
|
| 6 |
tags:
|
| 7 |
+
- Image-to-Text
|
| 8 |
+
- OCR
|
| 9 |
+
- Image-Captioning
|
| 10 |
datasets:
|
| 11 |
+
- priyank-m/text_recognition_en_zh_clean
|
| 12 |
metrics:
|
| 13 |
+
- cer
|
| 14 |
---
|
| 15 |
|
| 16 |
Multilingual OCR (m_OCR) is a VisionEncoderDecoder model based on the concept of TrOCR for English and Chinese document text-recognition.
|