Tidy

app.py

@@ -29,8 +29,8 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 
 image_description = "" 
 # audio_output = ""
-global markdown_output
-global audio_output
+# global markdown_output
+# global audio_output
 
 
 def check_hallucination(assertion, citation):
@@ -139,6 +139,7 @@ def process_speech(input_language, audio_input):
     except Exception as e:
         return f"{e}"
 
+
 def convert_text_to_speech(input_text: str, source_language: str, target_language: str) -> tuple[str, str]:
     client = Client("https://facebook-seamless-m4t.hf.space/--replicas/8cllp/")
 
@@ -153,11 +154,7 @@ def convert_text_to_speech(input_text: str, source_language: str, target_languag
             target_language,  
             api_name="/run",  
         )
-
-        # Check if the result is valid
-        if not result:
-            raise ValueError("No result returned from text-to-speech service")
-
+        
         # Initialize variables
         translated_text = ""
         audio_file_path = ""
@@ -176,13 +173,11 @@ def convert_text_to_speech(input_text: str, source_language: str, target_languag
                 audio_file_path = save_audio(item)  # Save the audio file
                 break
 
-        if not audio_file_path:
-            raise ValueError("No audio file path returned from text-to-speech service")
-
         return audio_file_path, translated_text
 
     except Exception as e:
-        return "", f"Error in text-to-speech conversion: {str(e)}"
+        return f"Error in text-to-speech conversion: {str(e)}", ""
+
 
 def process_image(image_input):
     # Initialize the Gradio client with the URL of the Gradio server
@@ -515,10 +510,12 @@ languages = {
     "Vietnamese": "vie"
 }
 
+
 def clear():
     # Return default values for each component
     return "English", None, None, "", None
 
+
 def create_interface():
     # with gr.Blocks(theme='ParityError/Anime') as iface:
     with gr.Blocks(theme='ParityError/Anime') as interface:
@@ -532,16 +529,16 @@ def create_interface():
 
         # Create a dropdown for language selection
         input_language = gr.Dropdown(input_language_options, label="Select the language", value="English", interactive=True)
-
+        
         with gr.Accordion("Use Voice", open=False) as voice_accordion:
             audio_input = gr.Audio(label="Speak")
             audio_output = gr.Markdown(label="Output text")  # Markdown component for audio
-            gr.Examples([["audio1.wav"],["audio2.wav"],],inputs=[audio_input])
+            gr.Examples([["audio1.wav"], ["audio2.wav"], ], inputs=[audio_input])
 
         with gr.Accordion("Use a Picture", open=False) as picture_accordion:
             image_input = gr.Image(label="Upload image")
             image_output = gr.Markdown(label="Output text")  # Markdown component for image
-            gr.Examples([["image1.png"], ["image2.jpeg"], ["image3.jpeg"],],inputs=[image_input])
+            gr.Examples([["image1.png"], ["image2.jpeg"], ["image3.jpeg"], ], inputs=[image_input])
 
         with gr.Accordion("MultiMed", open=False) as multimend_accordion:
             text_input = gr.Textbox(label="Use Text", lines=3, placeholder="I have had a sore throat and phlegm for a few days and now my cough has gotten worse!")
@@ -555,7 +552,7 @@ def create_interface():
                 ["بکل ہرپس کا صحیح علاج کیا ہے؟"],
                 ["구강 헤르페스의 적절한 치료법은 무엇입니까?"],
                 ["Je, ni matibabu gani sahihi kwa herpes ya buccal?"],
-            ],inputs=[text_input])
+            ], inputs=[text_input])
 
         text_output = gr.Markdown(label="MultiMed")  
         audio_output = gr.Audio(label="Audio Out", type="filepath")
@@ -569,5 +566,5 @@ def create_interface():
     return interface
 
 
-interface = create_interface()
-interface.launch(show_error=True, debug=True)
+app = create_interface()
+app.launch(show_error=True, debug=True)