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")# pip install -U transformers accelerate # 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 generation_config.json from PiotrSty/trocr-pl-base: direct link, hf CLI and curl.
- Browser
- Download file 198 Bytes
-
https://huggingface.co/PiotrSty/trocr-pl-base/resolve/main/generation_config.json
- Command line
-
hf download hf://PiotrSty/trocr-pl-base/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/PiotrSty/trocr-pl-base/resolve/main/generation_config.json
198 Bytes
| { | |
| "bos_token_id": 0, | |
| "decoder_start_token_id": 2, | |
| "early_stopping": true, | |
| "eos_token_id": 2, | |
| "max_length": 128, | |
| "num_beams": 4, | |
| "pad_token_id": 1, | |
| "transformers_version": "4.57.6" | |
| } | |