Instructions to use microsoft/trocr-base-handwritten with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/trocr-base-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="microsoft/trocr-base-handwritten")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-base-handwritten") model = AutoModelForImageTextToText.from_pretrained("microsoft/trocr-base-handwritten") - Notebooks
- Google Colab
- Kaggle
Unknown Token Problem with Swedish Characters in TrOCR
#18 opened 7 months ago
by
fendraq
Adding ONNX file of this model
#17 opened 8 months ago
by
Ryozan89
trtr
#16 opened 9 months ago
by
sdsd456457541
ocre
#15 opened 9 months ago
by
sdsd456457541
add AIBOM
#14 opened 11 months ago
by
sabato-nocera
finetuning trocr with qlora
#13 opened about 1 year ago
by
sriram369
Upload tokenizer.json
#11 opened over 1 year ago
by
iamvery
Add License
#10 opened over 1 year ago
by
gulnaz99
how to fine-tune it on multiple language handwritten text
7
#9 opened over 1 year ago
by
GardensOfBabylon29
TrOCR deployment in production
1
#6 opened almost 2 years ago
by
CristianJD
Full Page OCR
5
#5 opened over 2 years ago
by
DDM007