Image-to-Text
Transformers
PyTorch
TensorBoard
English
vision-encoder-decoder
image-text-to-text
Generated from Trainer
Instructions to use DunnBC22/trocr-base-printed_captcha_ocr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DunnBC22/trocr-base-printed_captcha_ocr 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="DunnBC22/trocr-base-printed_captcha_ocr")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("DunnBC22/trocr-base-printed_captcha_ocr") model = AutoModelForImageTextToText.from_pretrained("DunnBC22/trocr-base-printed_captcha_ocr") - Notebooks
- Google Colab
- Kaggle
Error using Inference API
#5
by jerry050512 - opened
When I uploaded an image, it outputs:
Can't load tokeniger using from_pretrained, please update its configuration: <class 'transformers.models.r_decoder.VisionEncoderDecoderConfig'>ision_encoder_decoder.VisionEncoderDecoderConfig'>