Instructions to use microsoft/trocr-large-handwritten with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/trocr-large-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-large-handwritten")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-large-handwritten") model = AutoModelForImageTextToText.from_pretrained("microsoft/trocr-large-handwritten") - Notebooks
- Google Colab
- Kaggle
add AIBOM
#12 opened 11 months ago
by
sabato-nocera
Delete .gitattributes
#11 opened over 1 year ago
by
jaunito28
How to Fine-tune TrOCR-large-handwritten on specifique langage
#10 opened over 1 year ago
by
GardensOfBabylon29
Adding `safetensors` variant of this model
1
#9 opened almost 2 years ago
by
SFconvertbot
ValueError: decoder_start_token_id....
#7 opened about 2 years ago
by
Ruzwaahn
Adding `safetensors` variant of this model
#6 opened over 2 years ago
by
SFconvertbot
How do I use it for multiple lines of handwritten text?
👍 1
3
#5 opened almost 3 years ago
by
abhikatta
Is there a way to get the recognition scores?
1
#4 opened almost 3 years ago
by
mfg12
warnings when loading the model
#3 opened about 3 years ago
by
chrisxx
Unable to train model: CUDA out of memory
1
#2 opened about 3 years ago
by
Pelpuo