Update app.py

app.py

@@ -1,21 +1,68 @@
 import gradio as gr
 from transformers import pipeline
+from PIL import Image
 
-text_emotion = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", return_all_scores=True)
+TEXT_MODEL  = "j-hartmann/emotion-english-distilroberta-base"   
+IMAGE_MODEL = "trpakov/vit-face-expression"                     
+AUDIO_MODEL = "superb/hubert-large-superb-er"                   
 
-def analyze_emotion(text):
-    results = text_emotion(text)[0]
-    results = sorted(results, key=lambda x: x['score'], reverse=True)
-    output = {r['label']: round(r['score'], 3) for r in results}
-    return output
+text_pipe  = pipeline("text-classification",  model=TEXT_MODEL,  return_all_scores=True)
+image_pipe = pipeline("image-classification", model=IMAGE_MODEL, top_k=None)
+audio_pipe = pipeline("audio-classification", model=AUDIO_MODEL, top_k=None)
 
-demo = gr.Interface(
-    fn=analyze_emotion,
-    inputs=gr.Textbox(lines=3, placeholder="Type something here..."),
-    outputs=gr.Label(num_top_classes=3),
-    title="Empath AI - Emotion Detection",
-    description="Type a sentence to see what emotions it contains!"
-)
+def _as_label_dict(preds):
+    
+    preds_sorted = sorted(preds, key=lambda p: p["score"], reverse=True)
+    return {p["label"]: float(round(p["score"], 4)) for p in preds_sorted}
 
-if __name__ == "__main__":
-    demo.launch()
+def analyze_text(text: str):
+    if not text or not text.strip():
+        return {"(enter some text)": 1.0}
+    preds = text_pipe(text)[0]
+    return _as_label_dict(preds)
+
+def analyze_face(img):
+    if img is None:
+        return {"(no image)": 1.0}
+    if isinstance(img, Image.Image):
+        pil = img
+    else:
+        pil = Image.fromarray(img)
+    preds = image_pipe(pil)
+    return _as_label_dict(preds)
+
+def analyze_voice(audio_path):
+    if audio_path is None:
+        return {"(no audio)": 1.0}
+    preds = audio_pipe(audio_path)  
+    return _as_label_dict(preds)
+
+with gr.Blocks(title="Empath AI — Multimodal Emotion Detection") as demo:
+    gr.Markdown(
+        """
+        # Empath AI — Emotion Detection (Text • Face • Voice)
+        Grant permission when the browser asks for **camera/microphone**.
+        Nothing is stored; analysis happens in memory and the scores are shown back to you.
+        """
+    )
+
+    with gr.Tab("Text"):
+        t_in  = gr.Textbox(label="Enter text", lines=3, placeholder="Type something here…")
+        t_btn = gr.Button("Analyze Text", variant="primary")
+        t_out = gr.Label(num_top_classes=3)
+        t_btn.click(analyze_text, inputs=t_in, outputs=t_out)
+
+    with gr.Tab("Face (Webcam or Upload)"):
+        i_in  = gr.Image(sources=["webcam", "upload"], type="pil", label="Webcam / Upload")
+        i_btn = gr.Button("Analyze Face", variant="primary")
+        i_out = gr.Label(num_top_classes=3)
+        i_btn.click(analyze_face, inputs=i_in, outputs=i_out)
+
+    with gr.Tab("Voice (Mic or Upload)"):
+        a_in  = gr.Audio(sources=["microphone", "upload"], type="filepath",
+                         label="Record or upload a short clip (≤30s)")
+        a_btn = gr.Button("Analyze Voice", variant="primary")
+        a_out = gr.Label(num_top_classes=3)
+        a_btn.click(analyze_voice, inputs=a_in, outputs=a_out)
+
+demo.launch()