update

app.py

@@ -154,21 +154,10 @@ def transcribe_and_speak(audio, source_lang, target_lang, youtube_url=None):
 def check_password(password):
     return password == DEVELOPER_PASSWORD
 
-def is_valid_youtube_url(url: str) -> bool:
-    pattern = r'(?:https?:\/\/)?(?:www\.)?(?:youtube\.com|youtu\.be)\/(?:watch\?v=)?(.+)'
-    return bool(re.match(pattern, url))
-
-def update_button_state(audio, youtube_url):
-    return gr.Button.update(interactive=bool(audio) or is_valid_youtube_url(youtube_url))
-
 def user_interface(audio, source_lang, target_lang, youtube_url):
     transcription, translated_text, audio_url = transcribe_and_speak(audio, source_lang, target_lang, youtube_url)
     return transcription, translated_text, audio_url
 
-def dev_interface(audio, source_lang, target_lang, youtube_url):
-    transcription, translated_text, audio_url = transcribe_and_speak(audio, source_lang, target_lang, youtube_url)
-    return transcription, translated_text, audio_url
-
 with gr.Blocks() as demo:
     gr.Markdown("# Speech Translation")
     
@@ -182,24 +171,13 @@ with gr.Blocks() as demo:
             user_target_lang = gr.Dropdown(choices=["en", "ma", "ta", "zh"], label="Target Language", value="zh")
         
         with gr.Row():
-            user_button = gr.Button("Translate and Speak", interactive=False)
+            user_button = gr.Button("Translate and Speak")
         
         with gr.Row():
             user_transcription_output = gr.Textbox(label="Transcription")
             user_translation_output = gr.Textbox(label="Translation")
             user_audio_output = gr.Audio(label="Translated Speech")
         
-        user_audio_input.change(
-            fn=update_button_state,
-            inputs=[user_audio_input, user_youtube_url],
-            outputs=[user_button]
-        )
-        user_youtube_url.change(
-            fn=update_button_state,
-            inputs=[user_audio_input, user_youtube_url],
-            outputs=[user_button]
-        )
-        
         user_button.click(
             fn=user_interface,
             inputs=[user_audio_input, user_source_lang, user_target_lang, user_youtube_url],
@@ -218,33 +196,25 @@ with gr.Blocks() as demo:
             
             with gr.Row():
                 dev_audio_input = gr.Audio(sources=["microphone", "upload"], type="filepath")
-                dev_youtube_url = gr.Textbox(label="YouTube URL (optional)")
                 dev_source_lang = gr.Dropdown(choices=["en", "ma", "ta", "zh"], label="Source Language", value="en")
                 dev_target_lang = gr.Dropdown(choices=["en", "ma", "ta", "zh"], label="Target Language", value="zh")
             
             with gr.Row():
-                dev_button = gr.Button("Translate and Speak", interactive=False)
+                dev_button = gr.Button("Transcribe, Translate, and Speak")
+            
+            with gr.Row():
+                dev_text_output = gr.Textbox(label="Transcription")
             
             with gr.Row():
-                dev_transcription_output = gr.Textbox(label="Transcription")
                 dev_translation_output = gr.Textbox(label="Translation")
-                dev_audio_output = gr.Audio(label="Translated Speech")
             
-            dev_audio_input.change(
-                fn=update_button_state,
-                inputs=[dev_audio_input, dev_youtube_url],
-                outputs=[dev_button]
-            )
-            dev_youtube_url.change(
-                fn=update_button_state,
-                inputs=[dev_audio_input, dev_youtube_url],
-                outputs=[dev_button]
-            )
+            with gr.Row():
+                dev_audio_output = gr.Audio(label="Translated Speech")
             
             dev_button.click(
-                fn=dev_interface,
-                inputs=[dev_audio_input, dev_source_lang, dev_target_lang, dev_youtube_url],
-                outputs=[dev_transcription_output, dev_translation_output, dev_audio_output]
+                fn=transcribe_and_speak,
+                inputs=[dev_audio_input, dev_source_lang, dev_target_lang],
+                outputs=[dev_text_output, dev_translation_output, dev_audio_output]
             )
         
         def login(password):