Spaces:

jfforero
/

Bello

Sleeping

App Files Files Community

jfforero commited on Aug 29, 2025

Commit

7b86b8d

verified ·

1 Parent(s): 5fefbfa

Update app.py

Browse files

Files changed (1) hide show

app.py +108 -4

app.py CHANGED Viewed

@@ -13,6 +13,8 @@ import torch
 import scipy.io.wavfile
 from transformers import AutoProcessor, MusicgenForConditionalGeneration
 import tempfile
 # Load the emotion prediction model
 def load_emotion_model(model_path):
@@ -183,6 +185,104 @@ def generate_image(emotion_prediction, transcribed_text):
         # Return a fallback image
         return Image.new('RGB', (1024, 512), color='white')
 # Function to get predictions
 def get_predictions(audio_input):
     emotion_prediction = predict_emotion_from_audio(audio_input)
@@ -201,7 +301,10 @@ def get_predictions(audio_input):
     # Generate music based on transcription and emotion
     music_path = generate_music(transcribed_text, emotion_prediction)
-    return emotion_prediction, transcribed_text, f"Sentiment: {sentiment} (Polarity: {polarity:.2f})", image, music_path
 # Create the Gradio interface
 interface = gr.Interface(
@@ -211,11 +314,12 @@ interface = gr.Interface(
         gr.Label(label="Acoustic Prediction"),
         gr.Label(label="Transcribed Text"),
         gr.Label(label="Sentiment Analysis"),
-        gr.Image(type='pil', label="Generated Image"),
-        gr.Audio(label="Generated Music", type="filepath")
     ],
     title="Affective Virtual Environments",
-    description="Create an AVE using your voice. Get emotion prediction, transcription, sentiment analysis, a generated image, and music."
 )
 interface.launch()

 import scipy.io.wavfile
 from transformers import AutoProcessor, MusicgenForConditionalGeneration
 import tempfile
+import base64
+import json
 # Load the emotion prediction model
 def load_emotion_model(model_path):
         # Return a fallback image
         return Image.new('RGB', (1024, 512), color='white')
+# Function to create HTML for 3D sphere with texture
+def create_sphere_viewer(image):
+    try:
+        # Convert PIL image to base64
+        buffered = BytesIO()
+        image.save(buffered, format="PNG")
+        img_str = base64.b64encode(buffered.getvalue()).decode()
+        # Create HTML with Three.js for 3D sphere
+        html_content = f"""
+        <!DOCTYPE html>
+        <html>
+        <head>
+            <style>
+                body {{ margin: 0; overflow: hidden; }}
+                canvas {{ display: block; }}
+            </style>
+        </head>
+        <body>
+            <script src="https://cdnjs.cloudflare.com/ajax/libs/three.js/r128/three.min.js"></script>
+            <script>
+                // Set up scene
+                const scene = new THREE.Scene();
+                const camera = new THREE.PerspectiveCamera(75, window.innerWidth / window.innerHeight, 0.1, 1000);
+                const renderer = new THREE.WebGLRenderer();
+                renderer.setSize(window.innerWidth, window.innerHeight);
+                document.body.appendChild(renderer.domElement);
+                // Create sphere with texture
+                const geometry = new THREE.SphereGeometry(5, 60, 40);
+                // Convert base64 image to texture
+                const textureLoader = new THREE.TextureLoader();
+                const texture = textureLoader.load('data:image/png;base64,{img_str}');
+                // Flip the texture for proper equirectangular mapping
+                texture.wrapS = THREE.RepeatWrapping;
+                texture.repeat.x = -1;
+                const material = new THREE.MeshBasicMaterial({{
+                    map: texture,
+                    side: THREE.DoubleSide
+                }});
+                const sphere = new THREE.Mesh(geometry, material);
+                scene.add(sphere);
+                // Position camera
+                camera.position.z = 8;
+                // Add controls for rotation
+                let mouseX = 0;
+                let mouseY = 0;
+                let targetX = 0;
+                let targetY = 0;
+                const windowHalfX = window.innerWidth / 2;
+                const windowHalfY = window.innerHeight / 2;
+                document.addEventListener('mousemove', (event) => {{
+                    mouseX = (event.clientX - windowHalfX);
+                    mouseY = (event.clientY - windowHalfY);
+                }});
+                // Animation loop
+                function animate() {{
+                    requestAnimationFrame(animate);
+                    targetX = mouseX * 0.001;
+                    targetY = mouseY * 0.001;
+                    sphere.rotation.y += 0.05 * (targetX - sphere.rotation.y);
+                    sphere.rotation.x += 0.05 * (targetY - sphere.rotation.x);
+                    renderer.render(scene, camera);
+                }}
+                animate();
+                // Handle window resize
+                window.addEventListener('resize', () => {{
+                    camera.aspect = window.innerWidth / window.innerHeight;
+                    camera.updateProjectionMatrix();
+                    renderer.setSize(window.innerWidth, window.innerHeight);
+                }});
+            </script>
+        </body>
+        </html>
+        """
+        # Save HTML to temporary file
+        with tempfile.NamedTemporaryFile(suffix=".html", delete=False, mode='w') as f:
+            f.write(html_content)
+            return f.name
+    except Exception as e:
+        print("Error creating sphere viewer:", e)
+        return None
 # Function to get predictions
 def get_predictions(audio_input):
     emotion_prediction = predict_emotion_from_audio(audio_input)
     # Generate music based on transcription and emotion
     music_path = generate_music(transcribed_text, emotion_prediction)
+    # Create 3D sphere viewer with the generated image as texture
+    sphere_html_path = create_sphere_viewer(image)
+    return emotion_prediction, transcribed_text, f"Sentiment: {sentiment} (Polarity: {polarity:.2f})", image, music_path, sphere_html_path
 # Create the Gradio interface
 interface = gr.Interface(
         gr.Label(label="Acoustic Prediction"),
         gr.Label(label="Transcribed Text"),
         gr.Label(label="Sentiment Analysis"),
+        gr.Image(type='pil', label="Generated Equirectangular Image"),
+        gr.Audio(label="Generated Music", type="filepath"),
+        gr.HTML(label="3D Sphere Viewer")  # Added HTML output for 3D sphere
     ],
     title="Affective Virtual Environments",
+    description="Create an AVE using your voice. Get emotion prediction, transcription, sentiment analysis, a generated equirectangular image, music, and a 3D sphere viewer."
 )
 interface.launch()