Image-to-Text
Transformers
Safetensors
Polish
English
vision-encoder-decoder
image-text-to-text
trocr
ocr
polish
historical-print
experimental
Eval Results (legacy)
Instructions to use PiotrSty/trocr-pl-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PiotrSty/trocr-pl-base 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="PiotrSty/trocr-pl-base")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("PiotrSty/trocr-pl-base") model = AutoModelForMultimodalLM.from_pretrained("PiotrSty/trocr-pl-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download selection.json from PiotrSty/trocr-pl-base: direct link, hf CLI and curl.
- Browser
- Download file 106 Bytes
-
https://huggingface.co/PiotrSty/trocr-pl-base/resolve/main/selection.json
- Command line
-
hf download hf://PiotrSty/trocr-pl-base/selection.json
-
curl -L -o selection.json https://huggingface.co/PiotrSty/trocr-pl-base/resolve/main/selection.json
106 Bytes
| { | |
| "best_checkpoint": "/kaggle/working/trocr-pl-run2/checkpoint-375", | |
| "best_cer": 0.04856512141280353 | |
| } |