updated
Browse files
README.md
CHANGED
|
@@ -21,6 +21,16 @@ This project is a web-based prototype that performs Optical Character Recognitio
|
|
| 21 |
Setup virtual environment using "python -m venv ocr-env"
|
| 22 |
and activated using "ocr-env\Scripts\activate"
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
## Features
|
| 25 |
- Upload an image in JPEG, PNG, or other common formats.
|
| 26 |
- Extract text from the uploaded image using EasyOCR.
|
|
|
|
| 21 |
Setup virtual environment using "python -m venv ocr-env"
|
| 22 |
and activated using "ocr-env\Scripts\activate"
|
| 23 |
|
| 24 |
+
## How can we run locally
|
| 25 |
+
Implement ocr and gradio(for user interface) in a python file(here I have app.py) save file and run it. We can run file using terminal by "python app.py" command. Gradio will launch the application and provide a local URL where we can test it in our browser.
|
| 26 |
+
|
| 27 |
+
## Deployment Process
|
| 28 |
+
- I have deployed this application on Hugging Face Spaces.
|
| 29 |
+
- To deploy on Hugging Face Spaces:
|
| 30 |
+
- 1.Create a repository on Hugging Face under the Spaces tab.
|
| 31 |
+
- 2.Add app.py file and requirements.txt file that lists all dependencies
|
| 32 |
+
- 3.Push the repository to Hugging Face, and it will automatically deploy the application.
|
| 33 |
+
|
| 34 |
## Features
|
| 35 |
- Upload an image in JPEG, PNG, or other common formats.
|
| 36 |
- Extract text from the uploaded image using EasyOCR.
|