Image-to-Text
Transformers
PyTorch
TensorBoard
Arabic
vision-encoder-decoder
image-text-to-text
Eval Results (legacy)
Instructions to use gagan3012/ArOCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gagan3012/ArOCR 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="gagan3012/ArOCR")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("gagan3012/ArOCR") model = AutoModelForMultimodalLM.from_pretrained("gagan3012/ArOCR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,5 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
-
- trocr
|
| 4 |
- image-to-text
|
| 5 |
language: ar
|
| 6 |
model-index:
|
|
@@ -12,7 +11,7 @@ model-index:
|
|
| 12 |
metrics:
|
| 13 |
- name: Test CER
|
| 14 |
type: cer
|
| 15 |
-
value:
|
| 16 |
---
|
| 17 |
|
| 18 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
|
|
|
| 3 |
- image-to-text
|
| 4 |
language: ar
|
| 5 |
model-index:
|
|
|
|
| 11 |
metrics:
|
| 12 |
- name: Test CER
|
| 13 |
type: cer
|
| 14 |
+
value: 0.02
|
| 15 |
---
|
| 16 |
|
| 17 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|