Update README.md

README.md

@@ -1,7 +1,19 @@
 ---
 license: mit
+tags:
+- vision-transformer
+- spectrogram-analysis
+- lora
+- pytorch
+- regression
+- bioacoustics
+widget:
+  - src: https://example.com/sample_spectrogram.jpg
+    task: audio-to-audio
 ---
 
+# Vision Transformer (ViT) with LoRA for Spectrogram Regression
+
 <div style="display: flex; flex-wrap: wrap; gap: 15px; margin-top: 15px;">
     <div style="flex: 1; min-width: 200px; background: white; border-radius: 8px; padding: 15px; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
         <h4 style="margin-top: 0; color: #5f6368;">🧑‍💻 Curated by</h4>
@@ -17,76 +29,19 @@ license: mit
     </div>
 </div>
 
-<div style="background: #f8f9fa; border-radius: 8px; padding: 20px; margin: 20px 0; border-left: 4px solid #4285f4;">
-<h2 style="margin-top: 0;">🔍 Model Architecture</h2>
-<div style="background: white; border-radius: 8px; padding: 15px; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
-    <h3 style="margin-top: 0;">Vision Transformer (ViT) with LoRA for Spectrogram Regression</h3>
-    
-    <div style="margin-bottom: 15px;">
-        <h4 style="margin-bottom: 10px;">Fine-Tuning Details</h4>
-        <table style="width: 100%; border-collapse: collapse;">
-            <tr>
-                <td style="padding: 8px; border-bottom: 1px solid #eee; width: 30%;"><strong>Framework</strong></td>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;">PyTorch</td>
-            </tr>
-            <tr>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;"><strong>Architecture</strong></td>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;">Pre-trained Vision Transformer (ViT)</td>
-            </tr>
-            <tr>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;"><strong>Adaptation Method</strong></td>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;">LoRA (Low-Rank Adaptation)</td>
-            </tr>
-            <tr>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;"><strong>Task</strong></td>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;">Regression on time-frequency representations</td>
-            </tr>
-            <tr>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;"><strong>Target Variables</strong></td>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;">
-                    1. Chirp start time (ms)<br>
-                    2. Start frequency (kHz)<br>
-                    3. End frequency (kHz)
-                </td>
-            </tr>
-            <tr>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;"><strong>Training Protocol</strong></td>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;">
-                    • Automatic Mixed Precision (AMP)<br>
-                    • Early stopping<br>
-                    • Learning Rate scheduling
-                </td>
-            </tr>
-            <tr>
-                <td style="padding: 8px;"><strong>Output</strong></td>
-                <td style="padding: 8px;">Quantitative predictions + optional natural language descriptions</td>
-            </tr>
-        </table>
-    </div>
+## Model Description
 
-    <div>
-        <h4 style="margin-bottom: 10px;">Resource Details</h4>
-        <table style="width: 100%; border-collapse: collapse;">
-            <tr>
-                <td style="padding: 8px; border-bottom: 1px solid #eee; width: 30%;"><strong>Trained Vision Transformer Model</strong></td>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;"><a href="https://huggingface.co/nubahador/Fine_Tuned_Transformer_Model_for_Chirp_Localization/tree/main">HuggingFace Model Hub</a></td>
-            </tr>
-            <tr>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;"><strong>Synthetic Spectrogram Dataset</strong></td>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;"><a href="https://huggingface.co/datasets/nubahador/ChirpLoc100K___A_Synthetic_Spectrogram_Dataset_for_Chirp_Localization/tree/main">HuggingFace Dataset Hub</a></td>
-            </tr>
-            <tr>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;"><strong>PyTorch Implementation</strong></td>
-                <td style="padding: 8px; border-bottom: 1px solid #eee;"><a href="https://github.com/nbahador/Train_Spectrogram_Transformer">Implementation GitHub Repository</a></td>
-            </tr>
-            <tr>
-                <td style="padding: 8px;"><strong>Synthetic Chirp Generator</strong></td>
-                <td style="padding: 8px;"><a href="https://github.com/nbahador/chirp_spectrogram_generator">Dataset GitHub Repository</a></td>
-            </tr>
-        </table>
-    </div>
-</div>
-</div>
+This is a Vision Transformer (ViT) model fine-tuned using Low-Rank Adaptation (LoRA) for regression tasks on spectrogram data. The model predicts three key parameters of chirp signals:
+1. Chirp start time (ms)
+2. Start frequency (kHz)
+3. End frequency (kHz)
+
+### Architecture
+
+- **Base Model**: Pre-trained Vision Transformer (ViT)
+- **Adaptation Method**: LoRA (Low-Rank Adaptation)
+- **Framework**: PyTorch
+- **Task**: Regression on time-frequency representations
 
 <div style="background: #f8f9fa; border-radius: 8px; padding: 20px; margin-bottom: 20px; border-left: 4px solid #ea4335;">
 <h2 style="margin-top: 0;">🔗 Dataset Sources</h2>