bug fixes

.env

@@ -1,2 +1,2 @@
 CO_API_KEY=KQBPf0H0ENZESIC5nuUJ4i4jjg34xMPAkYK7s31W
-SEAMLESSM4T=https://facebook-seamless-m4t-v2-large.hf.space/--replicas/v4gsf/ 
+SEAMLESSM4T=facebook/seamless-m4t-v2-large

app.py

@@ -278,6 +278,7 @@ inputs = [
 
 outputs = [
     RichTextbox(label="Processed Text"),
+    gr.Audio(label="Audio"),
     gr.Textbox(label="Focus 1"),
     gr.Textbox(label="Translated Phrases 1"),
     gr.Audio(label="Audio Output (Native Language) 1"),
@@ -292,9 +293,9 @@ outputs = [
     gr.Audio(label="Audio Output (Target Language) 3")
 ]
 def update_outputs(inputlanguage, target_language, audio, image, text, file):
-    final_text, top_phrases, translations, audio_outputs = process_input(
-    image=image, file=file, audio=audio, text=text, 
-    translateto=target_language, translatefrom=inputlanguage 
+    final_text, audio_output, top_phrases, translations, audio_outputs = process_input(
+        image=image, file=file, audio=audio, text=text, 
+        translateto=target_language, translatefrom=inputlanguage 
     )
     processed_text_output = final_text
     audio_output_native_phrases = [native for _, native in audio_outputs]
@@ -306,7 +307,8 @@ def update_outputs(inputlanguage, target_language, audio, image, text, file):
     audio_outputs_target = audio_output_target_phrases[:3]
 
     return (
-        processed_text_output, 
+        processed_text_output,
+        audio_output,  
         *audio_outputs_native, 
         *audio_outputs_target, 
         *longest_phrases_outputs, 
@@ -320,77 +322,4 @@ def interface_func(inputlanguage, target_language, audio, image, text, file):
 iface = gr.Interface(fn=interface_func, inputs=inputs, outputs=outputs, title=title, description=description)
 
 if __name__ == "__main__":
-    iface.launch()
-
-# def main():
-#     with gr.Blocks() as demo:
-#         gr.Markdown(title)
-#         gr.Markdown(description)
-        
-#         with gr.Row():
-#             input_language = gr.Dropdown(choices=choices, label="Your Native Language")
-#             target_language = gr.Dropdown(choices=choices, label="Language To Learn")
-        
-#         with gr.Accordion("Talk To 🌟AyaTonic"):
-#             with gr.Tab("🤙🏻Audio & Text"):
-#                 audio_input = gr.Audio(sources="microphone", type="filepath", label="Mic Input")
-#                 text_input = gr.Textbox(lines=2, label="Text Input")
-#             with gr.Tab("📸Image & File"):
-#                 image_input = gr.Image(type="pil", label="Camera Input")
-#                 file_input = gr.File(label="File Upload")
-        
-#         process_button = gr.Button("🌟AyaTonic")
-        
-#         processed_text_output = RichTextbox(label="Processed Text")
-#         longest_phrases_1 = gr.Textbox(label="Focus")
-#         translated_phrases_output_1 = gr.Textbox(label="Translated Phrases")
-#         audio_output_native_phrase_1 = gr.Audio(label="Audio Output (Native Language)")
-#         audio_output_target_phrase_1 = gr.Audio(label="Audio Output (Target Language)")
-#         longest_phrases_2 = gr.Textbox(label="Focus")
-#         translated_phrases_output_2 = gr.Textbox(label="Translated Phrases")
-#         audio_output_native_phrase_2 = gr.Audio(label="Audio Output (Native Language)")
-#         audio_output_target_phrase_2 = gr.Audio(label="Audio Output (Target Language)")
-#         longest_phrases_3 = gr.Textbox(label="Focus")
-#         translated_phrases_output_3 = gr.Textbox(label="Translated Phrases")
-#         audio_output_native_phrase_3 = gr.Audio(label="Audio Output (Native Language)")
-#         audio_output_target_phrase_3 = gr.Audio(label="Audio Output (Target Language)")
-        
-#         def update_outputs(image, file, audio, text, input_language, target_language):
-#             final_text, top_phrases, translations, audio_outputs = process_input(
-#                 image=image, file=file, audio=audio, text=text, 
-#                 translatefrom=input_language, translateto=target_language
-#             )
-
-#             processed_text_output = final_text
-#             audio_output_native_phrases = [native for _, native in audio_outputs]
-#             audio_output_target_phrases = [target for target, _ in audio_outputs]
-
-#             longest_phrases_outputs = top_phrases[:3]
-#             translated_phrases_outputs = translations[:3]
-#             audio_outputs_native = audio_output_native_phrases[:3]
-#             audio_outputs_target = audio_output_target_phrases[:3]
-
-#             return (
-#                 processed_text_output, 
-#                 *audio_outputs_native, 
-#                 *audio_outputs_target, 
-#                 *longest_phrases_outputs, 
-#                 *translated_phrases_outputs
-#             )
-       
-#         process_button.click(
-#             fn=update_outputs,
-#             inputs=[image_input, file_input, audio_input, text_input, input_language, target_language],
-#             outputs=[
-#                 processed_text_output, 
-#                 audio_output_native_phrase_1, audio_output_target_phrase_1, 
-#                 audio_output_native_phrase_2, audio_output_target_phrase_2, 
-#                 audio_output_native_phrase_3, audio_output_target_phrase_3, 
-#                 longest_phrases_1, translated_phrases_output_1, 
-#                 longest_phrases_2, translated_phrases_output_2, 
-#                 longest_phrases_3, translated_phrases_output_3
-#             ]
-#         )
-
-# if __name__ == "__main__":
-#     main()
+    iface.launch()