Image-to-Text
Transformers
Safetensors
Sinhala
vision-encoder-decoder
image-text-to-text
ocr
handwriting
sinhala
trocr
Instructions to use SriDoc/TrOCR-Sin-Handwritten with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SriDoc/TrOCR-Sin-Handwritten 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="SriDoc/TrOCR-Sin-Handwritten")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("SriDoc/TrOCR-Sin-Handwritten") model = AutoModelForMultimodalLM.from_pretrained("SriDoc/TrOCR-Sin-Handwritten", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from SriDoc/TrOCR-Sin-Handwritten: direct link, hf CLI and curl.
- Browser
- Download file 4.73 kB
-
https://huggingface.co/SriDoc/TrOCR-Sin-Handwritten/resolve/main/training_args.bin
- Command line
-
hf download hf://SriDoc/TrOCR-Sin-Handwritten/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/SriDoc/TrOCR-Sin-Handwritten/resolve/main/training_args.bin
4.73 kB
- Xet hash:
- 0c484d2fbe62e477e26ff23a762360ebd673493f58a21d8b9ff9f5630a7e2d55
- Size of remote file:
- 4.73 kB
- SHA256:
- 02cbfcba2ade3384ce0b5f8838f4a07ff378fc6a41082a4b32fb8b460720b586
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.