Update README.md

README.md

@@ -1,52 +1,48 @@
-# Infant Cry Detection using Causal Temporal Representation
-
-This project focuses on detecting infant cries using a novel **causal temporal representation** framework. Our approach incorporates causal reasoning into the data-generating process (DGP) to improve the interpretability and reliability of cry detection systems. This repository provides the necessary resources to explore, train, and evaluate supervised models for this task, along with mathematical assumptions and metrics tailored for event-based evaluation.
+---
+language: en
+tags:
+  - audio-classification
+  - causal-representation
+  - infant-cry-detection
+license: mit
+datasets:
+  - custom-audio-dataset
+metrics:
+  - event-based-f1
+  - iou
+  - accuracy
+---
+
+# Infant Cry Detection Using Causal Temporal Representation
+
+This model detects infant cries using a novel **causal temporal representation** framework. By integrating causal reasoning into the data-generating process (DGP), the model aims to enhance the interpretability and reliability of cry detection systems. 
 
 ## Features
-- **Data Generating Process**: Based on mathematical causal assumptions, our DGP defines how audio features and annotations are causally connected.
-- **Supervised Models**: State-of-the-art supervised learning methods, including Bidirectional LSTM, Transformer, and MobileNet V2.
-- **Event-Based Metrics**: Evaluation metrics tailored for time-sensitive detection tasks, including event-based F1-score and IOU.
-- **Interactive Example**: A Jupyter Notebook with step-by-step demonstrations.
+- **Causal Data Generating Process**: Incorporates mathematical causal assumptions to define the relationship between audio features and annotations.
+- **Supervised Models**: Includes pre-trained state-of-the-art models:
+  - Bidirectional LSTM
+  - Transformer
+  - MobileNet V2
+- **Event-Based Metrics**: Tailored for time-sensitive detection tasks:
+  - Event-based F1-score
+  - Intersection over Union (IOU)
+- **Interactive Example**: Jupyter Notebook with step-by-step usage demonstrations.
 
 ![Causal Graph](https://huggingface.co/CAPYLEE/CRSTC/blob/main/casual_graph.png)
 
-## Repository Structure
-
-```plaintext
-.
-├── data/               # Audio data in .wav format
-├── labels/             # Annotation files corresponding to audio data (.TextGrid)
-├── metrics/            # Event-based evaluation metrics
-├── models/             # Pre-trained supervised models
-├── src/                # Core codebase
-├── experiment.ipynb    # Usage demonstration
-└── README.md           # Project description
-```
-
-### Directory Details
-
-- **data/**: Contains raw audio files in `.wav` format.
-  - Each audio file represents an infant cry recording.
-
-- **labels/**: Stores annotation files in `.TextGrid` format.
-  - Each `.TextGrid` file corresponds to an audio file and provides ground truth segmentations for cry events.
+---
 
-- **metrics/**: Houses the implementation of event-based metrics for evaluating the performance of models.
-  - Metrics include event-based F1-score and IOU, designed to measure temporal accuracy effectively.
+## How to Use
 
-- **models/**: Contains pre-trained supervised models for infant cry detection.
-  - Models include:
-    - Bidirectional LSTM
-    - Transformer
-    - MobileNet V2
+You can load the model directly from Hugging Face:
 
-- **src/**: Core implementation of the infant cry detection framework.
-  - Includes modules for data preprocessing, feature extraction, model training, and evaluation.
+```python
+from transformers import AutoModel
 
-- **experiment.ipynb**: A Jupyter Notebook with a simple use case example.
-  - Demonstrates how to load data, preprocess it, train a model, and evaluate its performance.
+# Load model
+model = AutoModel.from_pretrained("your-username/infant-cry-detection")
 
-For more details, refer to our accompanying research paper.
+# Example usage
+audio_features = ...  # Preprocessed audio features
+outputs = model(audio_features)
 
-## License
-This project is licensed under the MIT License. See the LICENSE file for more details.