Update app.py

app.py

@@ -130,6 +130,20 @@ def save_to_parquet(records: List[dict], output_dir: str, max_size_mb: int = 500
     
     return parquet_files
 
+def get_sample_files():
+    sample_dir = "Sample"
+    if not os.path.exists(sample_dir):
+        return []
+    
+    audio_extensions = {'.wav', '.mp3', '.flac', '.ogg', '.m4a', '.aac', '.zip'}
+    sample_files = []
+    
+    for file in os.listdir(sample_dir):
+        if Path(file).suffix.lower() in audio_extensions:
+            sample_files.append(os.path.join(sample_dir, file))
+    
+    return sample_files
+
 def process_audio(input_file):
     if input_file is None:
         return None, "Vui lòng upload file audio hoặc file zip!"
@@ -211,12 +225,33 @@ with gr.Blocks(title="Audio Transcription & Dataset Creator") as app:
                 label="Upload Audio File hoặc ZIP",
                 file_types=['.wav', '.mp3', '.flac', '.ogg', '.m4a', '.aac', '.zip']
             )
+            
+            sample_files = get_sample_files()
+            if sample_files:
+                gr.Markdown("### 📂 Hoặc chọn file mẫu:")
+                sample_dropdown = gr.Dropdown(
+                    choices=sample_files,
+                    label="Chọn file mẫu",
+                    interactive=True
+                )
+                load_sample_btn = gr.Button("📥 Load file mẫu", variant="secondary")
+            
             process_btn = gr.Button("🚀 Bắt đầu xử lý", variant="primary")
         
         with gr.Column():
             output_file = gr.File(label="📦 Tải về Dataset ZIP")
             status_text = gr.Textbox(label="📊 Trạng thái", lines=8)
     
+    if sample_files:
+        def load_sample(sample_path):
+            return sample_path
+        
+        load_sample_btn.click(
+            fn=load_sample,
+            inputs=sample_dropdown,
+            outputs=input_file
+        )
+    
     process_btn.click(
         fn=process_audio,
         inputs=input_file,
@@ -230,7 +265,7 @@ with gr.Blocks(title="Audio Transcription & Dataset Creator") as app:
     - Cột `transcription`: văn bản transcription
     - Cột `file_name`: đường dẫn dạng `audio/filename_00001.wav`
     - Các câu ngắn (< 2s) sẽ được gộp lại
-    - Format tên dạng: train-00000-of-00001.parquet
+    - Format tên: train-00000-of-00007.parquet
     """)
 
 if __name__ == "__main__":