Instructions to use microsoft/trocr-base-printed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/trocr-base-printed 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-printed")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-base-printed") model = AutoModelForImageTextToText.from_pretrained("microsoft/trocr-base-printed") - Notebooks
- Google Colab
- Kaggle
## 🚨Missing License
3
#15 opened 10 months ago
by
Schilder
LIcense Not Listed
#14 opened 11 months ago
by
NarenSEG
add AIBOM
#13 opened 11 months ago
by
sabato-nocera
Model Optimization
#12 opened about 1 year ago
by
mr-usman
Finetuning
#11 opened over 1 year ago
by
whoami02
how to download this model,anyone can tell me details,thanks lots
1
#8 opened over 2 years ago
by
okgood2023
a bug
2
#6 opened almost 3 years ago
by
zhangbo2008
Using batch of images with trOcr
#5 opened almost 3 years ago
by
JoaquimMoreau
How to properly trace this model?
#4 opened about 3 years ago
by
z0rz0rz0r
can I use this model to extract text from an entire document?
👍 1
4
#3 opened about 3 years ago
by
sergenti
Difference between "printed", "handwritten", "stage1" and "string" versions
1
#2 opened over 3 years ago
by
Einmalumdiewelt