A deep learning project to analyze sentiment in Nepali text using BERT (Bidirectional Encoder Representations from Transformers).
This project implements a sentiment analysis model for Nepali text using state-of-the-art deep learning techniques. The model can classify Nepali text into three sentiment categories:
- 😊 Positive (1)
- 😐 Neutral (2)
☹️ Negative (0)
For detailed understanding, please refer to the following documentation files:
-
- Project setup
- Installation guide
- Prerequisites
- Initial configuration
-
- Directory layout
- File descriptions
- Code organization
-
- Deep learning concepts
- BERT architecture
- Model implementation
- Training process
-
- Data format
- Preprocessing steps
- Label distribution
- Data cleaning
-
- Training configuration
- Hyperparameters
- Training process
- Loss & Accuracy plots
-
- Model inference
- Example code
- API documentation
- Best practices
-
- NLP basics
- Sentiment analysis theory
- BERT explanation
- Deep learning concepts
# Clone the repository
git clone https://github.com/saileshbro/ai-proj
# Install dependencies
pip install -r requirements.txt
# Run the notebook
jupyter notebook model_training.ipynb- Python 3.7+
- PyTorch
- CUDA (optional, for GPU support)
- Basic understanding of:
- Python programming
- Machine Learning concepts
- Neural Networks
- Natural Language Processing
- Create an issue for bugs/features
- Join our Discord Community
- Follow us on Twitter
This project is licensed under the MIT License - see the LICENSE.md file for details.
- Hugging Face team for BERT implementation
- PyTorch community
- Contributors to the Nepali language datasets