Image-to-Text
Transformers
Safetensors
Russian
English
vision-encoder-decoder
image-text-to-text
htr
trocr
Instructions to use Daniil-Domino/trocr-base-ru-dialectic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Daniil-Domino/trocr-base-ru-dialectic 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="Daniil-Domino/trocr-base-ru-dialectic")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Daniil-Domino/trocr-base-ru-dialectic") model = AutoModelForMultimodalLM.from_pretrained("Daniil-Domino/trocr-base-ru-dialectic") - Notebooks
- Google Colab
- Kaggle
| { | |
| "́": 50265, | |
| "̂": 50266, | |
| "̄": 50267, | |
| "̆": 50269, | |
| "̑": 50268, | |
| "‿": 50270 | |
| } | |