commit

index.html

@@ -353,6 +353,30 @@
             </ul>
         </section>
 
+        <!-- Audio Sample -->
+        <section class="card">
+            <h2>Test Audio Sample</h2>
+            <p>Listen to the audio sample used for this evaluation:</p>
+            <div style="margin: 20px 0;">
+                <audio controls style="width: 100%; max-width: 600px;">
+                    <source src="eval/eval/test-audio.wav" type="audio/wav">
+                    Your browser does not support the audio element.
+                </audio>
+            </div>
+        </section>
+
+        <!-- Ground Truth Transcription -->
+        <section class="card">
+            <h2>Ground Truth Transcription</h2>
+            <p class="chart-subtitle">Reference transcription used to evaluate all models</p>
+            <div style="background-color: #f8f9fa; padding: 20px; border-radius: 8px; border-left: 4px solid #6366f1; line-height: 1.8; font-family: Georgia, serif;">
+                <p style="margin: 0;">I once wandered through a coastal town that smelled like sea salt and fresh bread. The locals said the tide wrote stories on the sand—short tales at low tide, epics when the moon grew bold. Every morning the boardwalk baker pulled loaves out of a brick oven, tapping the crusts so they sang a hollow, golden note. Kids would line up for the first slice, steam fogging their glasses while gulls staged slow-motion dives overhead. The best part was the lighthouse keeper, who claimed he could forecast the weather by listening to the bells on distant fishing boats. If the chimes sounded playful, the day would be calm; if they rang flat, storms stampeded in. I never learned whether his method worked, but I liked believing in a town where music, bread, and tides kept time together.</p>
+            </div>
+            <p style="margin-top: 15px; font-size: 0.9em; color: #666;">
+                <strong>Word count:</strong> 137 words
+            </p>
+        </section>
+
         <!-- Footer -->
         <footer class="footer">
             <p>Generated by automated Whisper evaluation framework</p>
@@ -418,8 +442,9 @@
                 },
                 scales: {
                     y: {
-                        beginAtZero: true,
-                        max: 100,
+                        beginAtZero: false,
+                        min: 82,
+                        max: 96,
                         title: {
                             display: true,
                             text: 'Transcription Accuracy (%)'
@@ -483,8 +508,9 @@
                 },
                 scales: {
                     y: {
-                        beginAtZero: true,
-                        max: 100,
+                        beginAtZero: false,
+                        min: 88,
+                        max: 96,
                         title: {
                             display: true,
                             text: 'Accuracy (%)'
@@ -611,8 +637,9 @@
                 },
                 scales: {
                     y: {
-                        beginAtZero: true,
-                        max: 100,
+                        beginAtZero: false,
+                        min: 74,
+                        max: 92,
                         title: {
                             display: true,
                             text: 'Information Preserved (%)'