Image-to-Text
Transformers
PyTorch
ONNX
Safetensors
vision-encoder-decoder
image-text-to-text
ocr
image to latex
Instructions to use OleehyO/TexTeller with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OleehyO/TexTeller 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="OleehyO/TexTeller")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("OleehyO/TexTeller") model = AutoModelForImageTextToText.from_pretrained("OleehyO/TexTeller") - Notebooks
- Google Colab
- Kaggle
How to call this from Sagemaker endpoint?
#2
by Osamaalam - opened
Do we need to provide image link or its path or base64?
Can you provide a proper sagemaker endpoint implementation?
ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400) from primary with message "{
"code": 400,
"type": "InternalServerException",
"message": "/.sagemaker/mms/models/OleehyO__TexTeller does not appear to have a file named preprocessor_config.json. Checkout \u0027https://huggingface.co//.sagemaker/mms/models/OleehyO__TexTeller/None\u0027 for available files."
}