feat: app

app.py

@@ -1,30 +1,13 @@
-# import gradio as gr
+import gradio as gr
 from ultralytics import YOLO
+import speech_recognition as sr
 
 model = YOLO('yolo11n-pose.pt')
 
-def poseImage(image):
+def proses_image(image):
     results = model(image)
     return results[0].plot()
 
-# interface = gr.Interface(
-#     fn=poseImage,
-#     inputs=gr.Image(streaming=True),
-#     outputs=gr.Image(),
-#     live=True
-# )
-
-# interface.launch()
-
-import gradio as gr
-import speech_recognition as sr
-from PIL import Image
-
-# Fungsi untuk memproses gambar
-def process_image(image):
-    return image  # Mengembalikan gambar yang sama
-
-# Fungsi untuk memproses audio
 def process_audio(audio):
     recognizer = sr.Recognizer()
     with sr.AudioFile(audio) as source:
@@ -37,49 +20,32 @@ def process_audio(audio):
         except sr.RequestError as e:
             return f"Error dengan layanan pengenalan suara: {e}"
 
-# Interface Gradio
+def update_visibility(input):
+    if input == "Gambar":
+        return gr.Row(visible=True), gr.Row(visible=False)
+    elif input == "Audio":
+        return gr.Row(visible=False), gr.Row(visible=True)
+
 with gr.Blocks() as demo:
     with gr.Row():
-        gr.Markdown("## Aplikasi Input Gambar/Audio")
-    
-    with gr.Row():
-        input_type = gr.Radio(["Gambar", "Audio"], label="Pilih Jenis Input", value="Gambar")
-
+        gr.Markdown("# Multimodal America Sign Language")
     with gr.Row():
-        with gr.Column():
-            image_input = gr.Image(type='numpy', label="Masukkan Gambar", visible=False)
-            audio_input = gr.Audio(sources="microphone", type="filepath", label="Masukkan Audio", visible=False)
-
-        with gr.Column():
-            image_output = gr.Image(label="Hasil Gambar", visible=False)
-            text_output = gr.Textbox(label="Hasil Audio", visible=False)
-    
-    # Fungsi untuk mengatur visibilitas berdasarkan jenis input
-    def update_visibility(input_type):
-        if input_type == "Gambar":
-            return (
-                gr.update(visible=True),
-                gr.update(visible=False),
-                gr.update(visible=True),
-                gr.update(visible=False),
-            )
-        elif input_type == "Audio":
-            return (
-                gr.update(visible=False),
-                gr.update(visible=True),
-                gr.update(visible=False),
-                gr.update(visible=True),
-            )
-
-    input_type.change(
-        update_visibility,
-        inputs=[input_type],
-        outputs=[image_input, audio_input, image_output, text_output],
-    )
-
-    # Menghubungkan input dengan output
-    image_input.change(poseImage, inputs=[image_input], outputs=[image_output])
-    audio_input.change(process_audio, inputs=[audio_input], outputs=[text_output])
+        input = gr.Radio(["Gambar", "Audio"], value="Gambar", label="Pilih mode:")
+    with gr.Row(visible=True) as gambar:
+        gr.Interface(
+            fn=proses_image,
+            inputs=gr.Image(streaming=True),
+            outputs=gr.Image(),
+            live=True
+        )
+    with gr.Row(visible=False) as audio:
+        gr.Interface(
+            fn=process_audio,
+            inputs=gr.Audio(sources="microphone", type="filepath", streaming=True),
+            outputs=gr.Textbox(),
+            live=True
+        )
+
+    input.change(update_visibility, inputs=[input], outputs=[gambar, audio])
 
-# Menjalankan aplikasi
 demo.launch()