Image-to-Text
Transformers
ONNX
Safetensors
vision-encoder-decoder
image-text-to-text
trocr
ocr
captcha
math-captcha
synthetic-data
Instructions to use arkhabbazan/ocr-math-captcha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use arkhabbazan/ocr-math-captcha with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="arkhabbazan/ocr-math-captcha")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("arkhabbazan/ocr-math-captcha") model = AutoModelForMultimodalLM.from_pretrained("arkhabbazan/ocr-math-captcha", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "bos_token_id": 0, | |
| "decoder_start_token_id": 0, | |
| "early_stopping": true, | |
| "eos_token_id": [ | |
| 2 | |
| ], | |
| "max_length": 32, | |
| "num_beams": 4, | |
| "pad_token_id": 1, | |
| "transformers_version": "4.57.6", | |
| "use_cache": false | |
| } | |