Update app.py

app.py

@@ -9,6 +9,8 @@ from deepface import DeepFace
 from transformers import pipeline
 # 如果不手动用 AutoTokenizer/AutoModel，就不必 import AutoTokenizer, AutoModelForSequenceClassification
 
+
+
 # --- 1. 加载 SVM 语音模型 ---
 print("Downloading SVM model from Hugging Face Hub...")
 model_path = hf_hub_download(repo_id="GCLing/emotion-svm-model", filename="svm_emotion_model.joblib")
@@ -158,36 +160,39 @@ def predict_face(img: np.ndarray):
         return {}
 
 # --- 5. Gradio 界面 ---
-with gr.Blocks() as demo:
-    gr.Markdown("## 多模態情緒分析示例")
-    with gr.Tabs():
-        # 臉部情緒 Tab
-        with gr.TabItem("臉部情緒"):
-            gr.Markdown("### 臉部情緒 (即時 Webcam Streaming 分析)")
-            with gr.Row():
-                webcam = gr.Image(sources="webcam", streaming=True, type="numpy", label="攝像頭畫面")
-                face_out = gr.JSON(label="情緒原始結果")
-            webcam.stream(fn=predict_face, inputs=webcam, outputs=face_out)
-        # 語音情緒 Tab
-        with gr.TabItem("語音情緒"):
-            gr.Markdown("### 語音情緒 分析")
-            with gr.Row():
-                audio = gr.Audio(sources="microphone", streaming=False, type="filepath", label="錄音")
+def build_interface():
+    with gr.Blocks() as demo:
+        gr.Markdown("## 多模態情緒分析示例")
+        with gr.Tabs():
+            # 臉部 Tab
+            with gr.TabItem("臉部情緒"):
+                gr.Markdown("### 臉部情緒 (即時 Webcam Streaming 分析)")
+                with gr.Row():
+                    webcam = gr.Image(tool="webcam", streaming=True, type="numpy", label="攝像頭畫面")
+                    face_out = gr.Label(label="情緒分布")
+                webcam.stream(fn=predict_face, inputs=webcam, outputs=face_out)
+
+            # 語音 Tab
+            with gr.TabItem("語音情緒"):
+                gr.Markdown("### 語音情緒 分析")
+                with gr.Row():
+                    audio = gr.Audio(source="microphone", streaming=False, type="filepath", label="錄音")
+                    voice_out = gr.Label(label="語音情緒結果")
+                audio.change(fn=predict_voice, inputs=audio, outputs=voice_out)
 
-                voice_out = gr.Label(label="語音情緒結果")
-            audio.change(fn=predict_voice, inputs=audio, outputs=voice_out)
-        # 文字情緒 Tab
-        with gr.TabItem("文字情緒"):
+            # 文字 Tab
+            with gr.TabItem("文字情緒"):
                 gr.Markdown("### 文字情緒 分析 (規則+zero-shot)")
                 with gr.Row():
                     text = gr.Textbox(lines=3, placeholder="請輸入中文文字…")
                     text_out = gr.Label(label="文字情緒結果")
-                # 可以用回車提交
-                btn = gr.Button("分析")
-                btn.click(fn=predict_text_mixed, inputs=text, outputs=text_out)
-    
-    
+                text.submit(fn=predict_text_mixed, inputs=text, outputs=text_out)
+                # 或按鈕：
+                # btn = gr.Button("分析")
+                # btn.click(fn=predict_text_mixed, inputs=text, outputs=text_out)
+        return demo
 
+# --- 4. 啟動 ---
 if __name__ == "__main__":
     demo = build_interface()
     demo.launch()