Update README.md

README.md

@@ -51,32 +51,32 @@ This model was developed using Assamese text data and trained with a custom toke
 The dataset was curated from public sources such as news articles, social media comments, and feedback forms, and was manually labeled into three sentiment classes: Positive, Neutral, and Negative.
 
 - 🏋️ Training Procedure
-✂️ Preprocessing: Text cleaning, tokenization using AssameseTokenizer, optional stemming and stopword removal
+- ✂️ Preprocessing: Text cleaning, tokenization using AssameseTokenizer, optional stemming and stopword removal
 
-🔢 Input Handling: Sequences padded or truncated to a fixed length of 512 tokens
+- 🔢 Input Handling: Sequences padded or truncated to a fixed length of 512 tokens
 
-🧠 Architecture: Embedding layer → LSTM → Dense (Softmax)
+- 🧠 Architecture: Embedding layer → LSTM → Dense (Softmax)
 
-💧 Regularization: Dropout layers to prevent overfitting
+- 💧 Regularization: Dropout layers to prevent overfitting
 
-⚙️ Optimizer: Adam
+- ⚙️ Optimizer: Adam
 
-🔁 Epochs: Trained for X epochs (replace with your actual number)
+- 🔁 Epochs: Trained for X epochs (replace with your actual number)
 
-📊 Evaluation: Final validation accuracy and F1-score: Insert actual metrics here
+- 📊 Evaluation: Final validation accuracy and F1-score: Insert actual metrics here
 
 ---
 
 ## 📦 Intended Usage
 Ideal for:
 
-🗨️ Social media sentiment tracking in Assamese
+- 🗨️ Social media sentiment tracking in Assamese
 
-📢 Public opinion & brand monitoring
+- 📢 Public opinion & brand monitoring
 
-📚 Research on low-resource NLP in Indic languages
+- 📚 Research on low-resource NLP in Indic languages
 
-⚠️ Limitations / Not Recommended For:
+- ⚠️ Limitations / Not Recommended For:
 
 Code-mixed Assamese-English input