Instructions to use microsoft/trocr-small-stage1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/trocr-small-stage1 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="microsoft/trocr-small-stage1")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-small-stage1") model = AutoModelForImageTextToText.from_pretrained("microsoft/trocr-small-stage1") - Notebooks
- Google Colab
- Kaggle
File size: 190 Bytes
d94c404 | 1 2 3 4 5 6 7 8 9 10 | {
"_from_model_config": true,
"bos_token_id": 0,
"decoder_start_token_id": 2,
"eos_token_id": 2,
"pad_token_id": 1,
"transformers_version": "4.27.0.dev0",
"use_cache": false
}
|