Update app.py

app.py

@@ -38,7 +38,8 @@ def create_DubIndic_interface():
             return (
                 "Please provide both an audio file and a target language.",
                 None, "", "", None, "",
-                gr.update(visible=False), gr.update(visible=False)
+                gr.update(visible=False), gr.update(visible=False),
+                None, gr.update(visible=False)
             )
         try:
             logger.info("Calling /process_audio_pipeline_step1 with file: %s", audio_file)
@@ -53,14 +54,16 @@ def create_DubIndic_interface():
             # [status, internal_val, orig_audio, trans, transl, dubbed_audio, progress]
             return (
                 result[0], result[2], result[3], result[4], result[5], result[6],
-                gr.update(visible=True), gr.update(visible=True) # Make edit and merge sections visible
+                gr.update(visible=True), gr.update(visible=True), # Make edit and merge sections visible
+                result[2] if result[2] else None, gr.update(visible=True if result[2] else False)
             )
         except Exception as e:
             logger.error("Error in start_processing: %s", e, exc_info=True)
             return (
                 f"Error starting the process: {e}",
                 None, "", "", None, "",
-                gr.update(visible=False), gr.update(visible=False)
+                gr.update(visible=False), gr.update(visible=False),
+                None, gr.update(visible=False)
             )
 
     def navigate_chunk(transcription, translation, direction):
@@ -77,10 +80,10 @@ def create_DubIndic_interface():
             logger.info("Received result from navigation: %s", result)
             # API returns a 6-element tuple
             # [internal_val, orig_audio, trans, transl, dubbed_audio, progress]
-            return result[1], result[2], result[3], result[4], result[5]
+            return result[1], result[2], result[3], result[4], result[5], result[1] if result[1] else None
         except Exception as e:
             logger.error("Error navigating chunks: %s", e, exc_info=True)
-            return None, f"Error navigating chunks: {e}", "", None, ""
+            return None, f"Error navigating chunks: {e}", "", None, "", None
 
     def generate_dubbed_chunk(transcription, translation):
         if not transcription and not translation:
@@ -195,7 +198,8 @@ def create_DubIndic_interface():
             with gr.Row():
                 prev_btn = gr.Button("◀️ Previous")
                 next_btn = gr.Button("Next ▶️")
-            original_audio = gr.Audio(label="Original Chunk Audio", type="filepath", interactive=False)
+            original_audio = gr.Audio(label="🎧 Original Chunk Audio", type="filepath", interactive=False)
+            download_original_audio = gr.File(label="💾 Download Original Chunk", visible=False)
             transcription_text = gr.Textbox(label="Transcription (edit if needed)", lines=2, interactive=True)
             translation_text = gr.Textbox(label="Translation (edit if needed)", lines=2, interactive=True)
             with gr.Row():
@@ -215,19 +219,19 @@ def create_DubIndic_interface():
         process_btn.click(
             fn=start_processing,
             inputs=[audio_input, lang_dropdown],
-            outputs=[step1_output, original_audio, transcription_text, translation_text, dubbed_audio, progress_text, edit_section, merge_section]
+            outputs=[step1_output, original_audio, transcription_text, translation_text, dubbed_audio, progress_text, edit_section, merge_section, download_original_audio, download_original_audio]
         )
         
         prev_btn.click(
             fn=lambda t, tr: navigate_chunk(t, tr, "prev"),
             inputs=[transcription_text, translation_text],
-            outputs=[original_audio, transcription_text, translation_text, dubbed_audio, progress_text]
+            outputs=[original_audio, transcription_text, translation_text, dubbed_audio, progress_text, download_original_audio]
         )
         
         next_btn.click(
             fn=lambda t, tr: navigate_chunk(t, tr, "next"),
             inputs=[transcription_text, translation_text],
-            outputs=[original_audio, transcription_text, translation_text, dubbed_audio, progress_text]
+            outputs=[original_audio, transcription_text, translation_text, dubbed_audio, progress_text, download_original_audio]
         )
 
         generate_btn.click(