Instructions to use coredog64/fao-speciescode-handwritten with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use coredog64/fao-speciescode-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="coredog64/fao-speciescode-handwritten")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("coredog64/fao-speciescode-handwritten") model = AutoModelForMultimodalLM.from_pretrained("coredog64/fao-speciescode-handwritten", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,4 +9,10 @@ base_model:
|
|
| 9 |
library_name: transformers
|
| 10 |
tags:
|
| 11 |
- image-to-text
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
library_name: transformers
|
| 10 |
tags:
|
| 11 |
- image-to-text
|
| 12 |
+
language:
|
| 13 |
+
- en
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
Handwritten text recognition model for [FAO Species Codes](https://www.fao.org/fishery/en/collection/asfis).
|
| 17 |
+
|
| 18 |
+
This model was explicitly trained with `transformers==4.35.2`. The same version should be used for inference.
|