Image-to-Text
Transformers
Safetensors
vision-encoder-decoder
image-text-to-text
vision
ocr
trocr
handwriting-recognition
document-processing
Instructions to use WARAJA/Tzefa-Word-OCR-TrOCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WARAJA/Tzefa-Word-OCR-TrOCR 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="WARAJA/Tzefa-Word-OCR-TrOCR")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("WARAJA/Tzefa-Word-OCR-TrOCR") model = AutoModelForImageTextToText.from_pretrained("WARAJA/Tzefa-Word-OCR-TrOCR") - Notebooks
- Google Colab
- Kaggle
Upload training_args.bin
Browse files- training_args.bin +3 -0
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf0f4c9a4430d38c64d4c2f1bbea25ace29210bf9a96471ac267330cb2c10899
|
| 3 |
+
size 4856
|