Update app.py

app.py

@@ -224,55 +224,56 @@ with playground:
         ## Speech Translator
         ## ================================================================================================================================
         with gr.TabItem("Speech Translator"):
-        gr.Markdown("""
-                    ## Your AI Translate Assistant
-                    ### Gets input audio from user, transcribe and translate it. Convert back to speech.
-                    - category: [Automatic Speech Recognition](https://huggingface.co/models?pipeline_tag=automatic-speech-recognition), model: [nvidia/canary-1b](https://huggingface.co/nvidia/canary-1b)
-                    - category: [Text-to-Speech](https://huggingface.co/models?pipeline_tag=text-to-speech), model: [facebook/mms-tts](https://huggingface.co/facebook/mms-tts)
-                    """)
+            with gr.Row():
+                gr.Markdown("""
+                        ## Your AI Translate Assistant
+                        ### Gets input audio from user, transcribe and translate it. Convert back to speech.
+                        - category: [Automatic Speech Recognition](https://huggingface.co/models?pipeline_tag=automatic-speech-recognition), model: [nvidia/canary-1b](https://huggingface.co/nvidia/canary-1b)
+                        - category: [Text-to-Speech](https://huggingface.co/models?pipeline_tag=text-to-speech), model: [facebook/mms-tts](https://huggingface.co/facebook/mms-tts)
+                        """)
+            
+            with gr.Row():
+                with gr.Column():
+                    source_lang = gr.Dropdown(
+                        choices=["en", "de", "es", "fr"], value="en", label="Source Language"
+                    )
+                with gr.Column():
+                    target_lang = gr.Dropdown(
+                        choices=["en", "de", "es", "fr"], value="fr", label="Target Language"
+                    )            
+        
+            with gr.Row():
+                with gr.Column():
+                    input_audio = gr.Audio(sources=["microphone"], type="filepath", label="Input Audio")            
+                with gr.Column():
+                    translated_speech = gr.Audio(type="filepath", label="Generated Speech")            
+        
+            with gr.Row():
+                with gr.Column():            
+                    transcipted_text = gr.Textbox(label="Transcription")
+                with gr.Column():            
+                    translated_text = gr.Textbox(label="Translation")
         
-        with gr.Row():
-            with gr.Column():
-                source_lang = gr.Dropdown(
-                    choices=["en", "de", "es", "fr"], value="en", label="Source Language"
+            with gr.Row():
+                with gr.Column():
+                    submit_button = gr.Button(value="Start Process", variant="primary")
+                with gr.Column():
+                    clear_button = gr.ClearButton(components=[input_audio, source_lang, target_lang, transcipted_text, translated_text, translated_speech], value="Clear")    
+        
+            with gr.Row():
+                gr.Examples(
+                    examples=[
+                        ["audio/sample_en.wav","en","fr"],
+                        ["audio/sample_fr.wav","fr","de"],
+                        ["audio/sample_de.wav","de","es"],
+                        ["audio/sample_es.wav","es","en"]
+                    ], 
+                    inputs=[input_audio, source_lang, target_lang], 
+                    outputs=[transcipted_text, translated_text, translated_speech], 
+                    run_on_click=True, cache_examples=True, fn=start_process
                 )
-            with gr.Column():
-                target_lang = gr.Dropdown(
-                    choices=["en", "de", "es", "fr"], value="fr", label="Target Language"
-                )            
-    
-        with gr.Row():
-            with gr.Column():
-                input_audio = gr.Audio(sources=["microphone"], type="filepath", label="Input Audio")            
-            with gr.Column():
-                translated_speech = gr.Audio(type="filepath", label="Generated Speech")            
-    
-        with gr.Row():
-            with gr.Column():            
-                transcipted_text = gr.Textbox(label="Transcription")
-            with gr.Column():            
-                translated_text = gr.Textbox(label="Translation")
-    
-        with gr.Row():
-            with gr.Column():
-                submit_button = gr.Button(value="Start Process", variant="primary")
-            with gr.Column():
-                clear_button = gr.ClearButton(components=[input_audio, source_lang, target_lang, transcipted_text, translated_text, translated_speech], value="Clear")    
-    
-        with gr.Row():
-            gr.Examples(
-                examples=[
-                    ["audio/sample_en.wav","en","fr"],
-                    ["audio/sample_fr.wav","fr","de"],
-                    ["audio/sample_de.wav","de","es"],
-                    ["audio/sample_es.wav","es","en"]
-                ], 
-                inputs=[input_audio, source_lang, target_lang], 
-                outputs=[transcipted_text, translated_text, translated_speech], 
-                run_on_click=True, cache_examples=True, fn=start_process
-            )
-                
-        submit_button.click(start_process, inputs=[input_audio, source_lang, target_lang], outputs=[transcipted_text, translated_text, translated_speech])
+                    
+            submit_button.click(start_process, inputs=[input_audio, source_lang, target_lang], outputs=[transcipted_text, translated_text, translated_speech])