Downloads · 30 days
0
Hindi-optical-character-recognition
vs393031/Hindi-optical-character-recognition
Hindi-optical-character-recognition is a machine learning model from vs393031. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
You can run the streamlit and gradio app locally.
Access
Public
Updated Feb 28, 2023
Repo size
12.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gif9.6 MB · 70%
At a glance
- Access
- Public
- Created
- Feb 28, 2023
- Updated
- Feb 28, 2023
- SHA
- 25a8f326
Model card
From the Hugging Face model README
Hindi-Character-Recognition
The app is live on huggingface spaces! Try it -> Gradio-HCR
Running the app locally:
You can run the streamlit and gradio app locally.
-
Install the requirements:
pip install -r requirements.txt -
Now, just do
streamlit run app.pyorgradio gradio_app.py
Streamlit demo
Gradio demo
Training the model (Optional)
-
Install the requirements:
pip install -r requirements.txt -
Hindi Character Recognition
Getting the data:
- Download the data from here
- Unzip it. You need to split the data into 4 different directories, since we are training for Hindi digits & letters separately.
How to run ?
- You can create your custom model in the
model.pyfile or can go with theHNetalready present. For custom models created, you need to import them totrain.py, for them to to use. Remember we are training different models for Hindi Digit & Characters. - Now to train the model with default params do,
python train.py. You can also specify epochs and lr. Most important, is themodel_type - To train do,
python train.py --epochs <num-epochs> --lr <learning-rate> --model_type <type-of-model>
- Created
- Feb 28, 2023
- Updated
- Feb 28, 2023