Instructions to use napatswift/test-ocr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use napatswift/test-ocr 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="napatswift/test-ocr")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("napatswift/test-ocr") model = AutoModelForImageTextToText.from_pretrained("napatswift/test-ocr") - Notebooks
- Google Colab
- Kaggle
| { | |
| "cls_token": "[CLS]", | |
| "do_basic_tokenize": true, | |
| "do_lower_case": false, | |
| "mask_token": "[MASK]", | |
| "model_max_length": 512, | |
| "name_or_path": "Geotrend/bert-base-th-cased", | |
| "never_split": null, | |
| "pad_token": "[PAD]", | |
| "processor_class": "TrOCRProcessor", | |
| "sep_token": "[SEP]", | |
| "special_tokens_map_file": null, | |
| "strip_accents": null, | |
| "tokenize_chinese_chars": true, | |
| "tokenizer_class": "BertTokenizer", | |
| "unk_token": "[UNK]" | |
| } | |