Introduced a clean and user-friendly Gradio interface for the Gooya Persian ASR system

Accepts Persian audio files (up to 30 seconds).
Returns both the transcription text and inference time.
Includes styling improvements such as custom labels, emojis for better UX, and a polished layout.
Added documentation and friendly descriptions for better usability.

app.py

@@ -34,17 +34,24 @@ def transcribe_audio(file_path):
 
 
 # Set up the Gradio interface
-gr.Interface(
-    fn=transcribe_audio,
-    inputs=gr.Audio(type="filepath"),
-    outputs=[
-        gr.Textbox(label="Transcription"),
-        gr.Textbox(label="Inference Time")
-    ],
-    title="Gooya v1.4 Persian ASR",
-    description="""
-The Gooya Persian ASR model is crazy fast and super [powerful](https://huggingface.co/spaces/navidved/open_persian_asr_leaderboard) when it comes to Persian ASR!
-    \nJust drop in a Persian audio file, and boom—we’ll hit you with the best transcription you can get! 🚀🔥
-    \n(The maximum time allowed for testing is 30 seconds.)
-"""
-).launch()
+def launch_interface():
+    gr.Interface(
+        fn=transcribe_audio,
+        inputs=gr.Audio(type="filepath", label="Upload Audio (Max 30s)"),
+        outputs=[
+            gr.Textbox(label="📝 Transcription"),
+            gr.Textbox(label="⏱️ Inference Time (s)")
+        ],
+        title="🗣️ Gooya v1.4 – Persian ASR",
+        description=(
+            "The **Gooya Persian ASR** model is crazy fast and incredibly [powerful]"
+            "(https://huggingface.co/spaces/navidved/open_persian_asr_leaderboard) "
+            "when it comes to Persian speech recognition!\n\n"
+            "🎤 Just drop a short Persian audio clip (max 30s), and boom — "
+            "you’ll get a top-notch transcription instantly. 🚀🔥"
+        ),
+        theme="default",
+        allow_flagging="never"
+    ).launch()
+
+launch_interface()